论文检索

Applications · Language, Speech and Dialog

Jiawei Zhou, Xiaoguang Li, Lifeng Shang, Xin Jiang, Qun Liu, Lei Chen

Disentangled representation learning remains challenging as the underlying factors of variation in the data do not naturally exist. The inherent complexity of real-world data makes it unfeasible to exhaustively enumerate and encapsulate all its variations within a finite set of factors. However, it is worth noting that most real-world data have linguistic equivalents, typically in the form of textual descriptions. These linguistic counterparts can represent the data and effortlessly decomposed into distinct tokens. In light of this, we present Vocabulary Disentangled Retrieval (VDR), a retrieval-based framework that harnesses natural language as proxies of the underlying data variation to drive disentangled representation learning. Our approach employ a bi-encoder model to represent both data and natural language in a vocabulary space, enabling the model to distinguish dimensions that capture intrinsic characteristics within data through its natural language counterpart, thus facilitating disentanglement. We extensively assess the performance of VDR across 15 retrieval benchmark datasets, covering text-to-text and cross-modal retrieval scenarios, as well as human evaluation. Our experimental results compellingly demonstrate the superiority of VDR over previous bi-encoder retrievers with comparable model size and training costs, achieving an impressive 8.7% improvement in NDCG@10 on the BEIR benchmark, a 5.3\% increase on MS COCO, and a 6.0% increase on Flickr30k in terms of mean recall in the zero-shot setting. Moreover, The results from human evaluation indicate that interpretability of our method is on par with SOTA captioning models.

Applications · Language, Speech and Dialog

Elisa Kreiss, Eric Zelikman, Christopher Potts, Nick Haber

Referenceless metrics (e.g., CLIPScore) use pretrained vision--language models to assess image descriptions directly without costly ground-truth reference texts. Such methods can facilitate rapid progress, but only if they truly align with human preference judgments. In this paper, we introduce ContextRef, a benchmark for assessing referenceless metrics for such alignment. ContextRef has two components: human ratings along a variety of established quality dimensions, and ten diverse robustness checks designed to uncover fundamental weaknesses. A crucial aspect of ContextRef is that images and descriptions are presented in context, reflecting prior work showing that context is important for description quality. Using ContextRef, we assess a variety of pretrained models, scoring functions, and techniques for incorporating context. None of the methods is successful with ContextRef, but we show that careful fine-tuning yields substantial improvements. ContextRef remains a challenging benchmark though, in large part due to the challenge of context dependence.

Applications · Language, Speech and Dialog

Behzad Shayegh, Yanshuai Cao, Xiaodan Zhu, Jackie Cheung, Lili Mou

We investigate the unsupervised constituency parsing task, which organizes words and phrases of a sentence into a hierarchical structure without using linguistically annotated data. We observe that existing unsupervised parsers capture different aspects of parsing structures, which can be leveraged to enhance unsupervised parsing performance.To this end, we propose a notion of "tree averaging," based on which we further propose a novel ensemble method for unsupervised parsing.To improve inference efficiency, we further distill the ensemble knowledge into a student model; such an ensemble-then-distill process is an effective approach to mitigate the over-smoothing problem existing in common multi-teacher distilling methods.Experiments show that our method surpasses all previous approaches, consistently demonstrating its effectiveness and robustness across various runs, with different ensemble components, and under domain-shift conditions.

Applications · Language, Speech and Dialog

Szu-Wei Fu, Kuo-Hsuan Hung, Yu Tsao, Yu-Chiang Frank Wang

Speech quality estimation has recently undergone a paradigm shift from human-hearing expert designs to machine-learning models. However, current models rely mainly on supervised learning, which is time-consuming and expensive for label collection. To solve this problem, we propose VQScore, a self-supervised metric for evaluating speech based on the quantization error of a vector-quantized-variational autoencoder (VQ-VAE). The training of VQ-VAE relies on clean speech; hence, large quantization errors can be expected when the speech is distorted. To further improve correlation with real quality scores, domain knowledge of speech processing is incorporated into the model design. We found that the vector quantization mechanism could also be used for self-supervised speech enhancement (SE) model training. To improve the robustness of the encoder for SE, a novel self-distillation mechanism combined with adversarial training is introduced. In summary, the proposed speech quality estimation method and enhancement models require only clean speech for training without any label requirements. Experimental results show that the proposed VQScore and enhancement model are competitive with supervised baselines. The code and pre-trained models will be released

Applications · Language, Speech and Dialog

Xin Zhang, Dong Zhang, Shimin Li, Yaqian Zhou, Xipeng Qiu

Current speech large language models build upon discrete speech representations,which can be categorized into semantic tokens and acoustic tokens. However,existing speech tokens are not specifically designed for speech language modeling. To assess the suitability of speech tokens for building speech languagemodels, we established the first benchmark, SLMTokBench. Our results indicatethat neither semantic nor acoustic tokens are ideal for this purpose. Therefore, wepropose SpeechTokenizer, a unified speech tokenizer for speech large languagemodels. SpeechTokenizer adopts the Encoder-Decoder architecture with residualvector quantization (RVQ). Unifying semantic and acoustic tokens, SpeechTokenizer disentangles different aspects of speech information hierarchically acrossdifferent RVQ layers. Furthermore, We construct a Unified Speech LanguageModel (USLM) leveraging SpeechTokenizer. Experiments show that SpeechTokenizer performs comparably to EnCodec in speech reconstruction and demonstratesstrong performance on the SLMTokBench benchmark. Also, USLM outperformsVALL-E in zero-shot Text-to-Speech tasks. Code and models are available athttps://github.com/ZhangXInFD/SpeechTokenizer/.

Applications · Language, Speech and Dialog

yisheng xiao, Juntao Li, Zechen Sun, Zechang Li, Qingrong Xia, Xinyu Duan, Zhefeng Wang, Min Zhang

Language modeling at scale has proven very effective and brought unprecedented success to natural language models. Many typical representatives, especially decoder-only models, e.g., BLOOM and LLaMA, and encoder-decoder models, e.g., Flan-T5 and AlexaTM, have exhibited incredible instruction-following capabilities while keeping strong task completion ability. These large language models can achieve superior performance in various tasks and even yield emergent capabilities, e.g., reasoning and universal generalization. Though the above two paradigms are mainstream and well explored, the potential of the BERT family, which are encoder-only based models and have ever been one of the most representative pre-trained models, also deserves attention, at least should be discussed. In this work, we adopt XML-R to explore the effectiveness of the BERT family for instruction following and zero-shot learning. We first design a simple yet effective strategy to utilize the encoder-only models for generation tasks and then conduct multi-task instruction tuning. Experimental results demonstrate that our fine-tuned model, Instruct-XMLR, outperforms Bloomz on all evaluation tasks and achieves comparable performance with mT0 on most tasks. Surprisingly, Instruct-XMLR also possesses strong task and language generalization abilities, indicating that Instruct-XMLR can also serve as a good instruction follower and zero-shot learner. Besides, Instruct-XMLR can accelerate decoding due to its non-autoregressive generation manner, achieving around 3 times speedup compared with current autoregressive large language models. Although we also witnessed several limitations through our experiments, such as the performance decline in long-generation tasks and the shortcoming of length prediction, Instruct-XMLR can still become a good member of the family of current large language models.

Applications · Language, Speech and Dialog

Eliya Nachmani, Alon Levkovitch, Roy Hirsch, Julian Salazar, Chulayuth Asawaroengchai, Soroosh Mariooryad, Ehud Rivlin, RJ Skerry-Ryan, Michele Tadmor Ramanovich

We present Spectron, a novel approach to adapting pre-trained large language models (LLMs) to perform spoken question answering (QA) and speech continuation. By endowing the LLM with a pre-trained speech encoder, our model becomes able to take speech inputs and generate speech outputs. The entire system is trained end-to-end and operates directly on spectrograms, simplifying our architecture. Key to our approach is a training objective that jointly supervises speech recognition, text continuation, and speech synthesis using only paired speech-text pairs, enabling a `cross-modal' chain-of-thought within a single decoding pass. Our method surpasses existing spoken language models in speaker preservation and semantic coherence. Furthermore, the proposed model improves upon direct initialization in retaining the knowledge of the original LLM as demonstrated through spoken QA datasets. We release our audio samples and spoken QA dataset via our website.

Deep Learning · Large Language Models

CHEN CHEN, Ruizhe Li, Yuchen Hu, Sabato Siniscalchi, Pin-Yu Chen, Ensiong Chng, Chao-Han Huck Yang

Recent studies have successfully shown that large language models (LLMs) can be successfully used for generative error correction (GER) on top of the automatic speech recognition (ASR) output. Specifically, an LLM is utilized to carry out a direct mapping from the N-best hypotheses list generated by an ASR system to the predicted output transcription. However, despite its effectiveness, GER introduces extra data uncertainty since the LLM is trained without taking into account acoustic information available in the speech signal. In this work, we aim to overcome such a limitation by infusing acoustic information before generating the predicted transcription through a novel late fusion solution termed Uncertainty-Aware Dynamic Fusion (UADF). UADF is a multimodal fusion approach implemented into an auto-regressive decoding process and works in two stages: (i) It first analyzes and calibrates the token-level LLM decision, and (ii) it then dynamically assimilates the information from the acoustic modality. Experimental evidence collected from various ASR tasks shows that UADF surpasses existing fusion mechanisms in several ways. It yields significant improvements in word error rate (WER) while mitigating data uncertainty issues in LLM and addressing the poor generalization relied with sole modality during fusion. We also demonstrate that UADF seamlessly adapts to audio-visual speech recognition.

Applications · Language, Speech and Dialog

Zeyu Liu, Gourav Datta, Anni Li, Peter Beerel

Transformer models have demonstrated high accuracy in numerous applications but have high complexity and lack sequential processing capability making them ill-suited for many streaming applications at the edge where devices are heavily resource-constrained. Thus motivated, many researchers have proposed reformulating the transformer models as RNN modules which modify the self-attention computation with explicit states. However, these approaches often incur significant performance degradation.The ultimate goal is to develop a model that has the following properties: parallel training, streaming and low-cost inference, and state-of-the-art (SOTA) performance. In this paper, we propose a new direction to achieve this goal. We show how architectural modifications to a fully-sequential recurrent model can help push its performance toward Transformer models while retaining its sequential processing capability. Specifically, inspired by the recent success of Legendre Memory Units (LMU) in sequence learning tasks, we propose LMUFormer, which augments the LMU with convolutional patch embedding and convolutional channel mixer. Moreover, we present a spiking version of this architecture, which introduces the benefit of states within the patch embedding and channel mixer modules while simultaneously reducing the computing complexity. We evaluated our architectures on multiple sequence datasets. Of particular note is our performance on the Speech Commands V2 dataset (35 classes). In comparison to SOTA transformer-based models within the ANN domain, our LMUFormer demonstrates comparable performance while necessitating a remarkable $70\times$ reduction in parameters and a substantial $140\times$ decrement in FLOPs. Furthermore, when benchmarked against extant low-complexity SNN variants, our model establishes a new SOTA with an accuracy of 96.12\%. Additionally, owing to our model's proficiency in real-time data processing, we are able to achieve a 32.03\% reduction in sequence length, all while incurring an inconsequential decline in performance.

Deep Learning · Generative Models and Autoencoders

Yichong Leng, ZHifang Guo, Kai Shen, Zeqian Ju, Xu Tan, Eric Liu, Yufei Liu, Dongchao Yang, leying zhang, Kaitao Song 等

Speech conveys more information than text, as the same word can be uttered in various voices to convey diverse information. Compared to traditional text-to-speech (TTS) methods relying on speech prompts (reference speech) for voice variability, using text prompts (descriptions) is more user-friendly since speech prompts can be hard to find or may not exist at all. TTS approaches based on the text prompt face two main challenges: 1) the one-to-many problem, where not all details about voice variability can be described in the text prompt, and 2) the limited availability of text prompt datasets, where vendors and large cost of data labeling are required to write text prompts for speech. In this work, we introduce PromptTTS 2 to address these challenges with a variation network to provide variability information of voice not captured by text prompts, and a prompt generation pipeline to utilize the large language models (LLM) to compose high quality text prompts. Specifically, the variation network predicts the representation extracted from the reference speech (which contains full information about voice variability) based on the text prompt representation. For the prompt generation pipeline, it generates text prompts for speech with a speech language understanding model to recognize voice attributes (e.g., gender, speed) from speech and a large language model to formulate text prompts based on the recognition results. Experiments on a large-scale (44K hours) speech dataset demonstrate that compared to the previous works, PromptTTS 2 generates voices more consistent with text prompts and supports the sampling of diverse voice variability, thereby offering users more choices on voice generation. Additionally, the prompt generation pipeline produces high-quality text prompts, eliminating the large labeling cost. The demo page of PromptTTS 2 is available (https://speechresearch.github.io/prompttts2).

Deep Learning · Generative Models and Autoencoders

Kai Shen, Zeqian Ju, Xu Tan, Eric Liu, Yichong Leng, Lei He, Tao Qin, sheng zhao, Jiang Bian

Scaling text-to-speech (TTS) to large-scale, multi-speaker, and in-the-wild datasets is important to capture the diversity in human speech such as speaker identities, prosodies, and styles (e.g., singing). Current large TTS systems usually quantize speech into discrete tokens and use language models to generate these tokens one by one, which suffer from unstable prosody, word skipping/repeating issue, and poor voice quality. In this paper, we develop NaturalSpeech 2, a TTS system that leverages a neural audio codec with residual vector quantizers to get the quantized latent vectors and uses a diffusion model to generate these latent vectors conditioned on text input. To enhance the zero-shot capability that is important to achieve diverse speech synthesis, we design a speech prompting mechanism to facilitate in-context learning in the diffusion model and the duration/pitch predictor. We scale NaturalSpeech 2 to large-scale datasets with 44K hours of speech and singing data and evaluate its voice quality on unseen speakers. NaturalSpeech 2 outperforms previous TTS systems by a large margin in terms of prosody/timbre similarity, robustness, and voice quality in a zero-shot setting, and performs novel zero-shot singing synthesis with only a speech prompt. Audio samples are available at https://naturalspeech2.github.io/.

Tianyu He, Junliang Guo, Runyi Yu, Yuchi Wang, jialiang zhu, Kaikai An, Leyi Li, Xu Tan, Chunyu Wang, Han Hu 等

Zero-shot talking avatar generation aims at synthesizing natural talking videos from speech and a single portrait image. Previous methods have relied on domain-specific heuristics such as warping-based motion representation and 3D Morphable Models, which limit the naturalness and diversity of the generated avatars. In this work, we introduce GAIA (Generative AI for Avatar), which eliminates the domain priors in talking avatar generation. In light of the observation that the speech only drives the motion of the avatar while the appearance of the avatar and the background typically remain the same throughout the entire video, we divide our approach into two stages: 1) disentangling each frame into motion and appearance representations; 2) generating motion sequences conditioned on the speech and reference portrait image. We collect a large-scale high-quality talking avatar dataset and train the model on it with different scales (up to 2B parameters). Experimental results verify the superiority, scalability, and flexibility of GAIA as 1) the resulting model beats previous baseline models in terms of naturalness, diversity, lip-sync quality, and visual quality; 2) the framework is scalable since larger models yield better results; 3) it is general and enables different applications like controllable talking avatar generation and text-instructed avatar generation.

Applications · Language, Speech and Dialog

Sahana Ramnath, Brihi Joshi, Skyler Hallinan, Ximing Lu, Liunian Li, Aaron Chan, Jack Hessel, Yejin Choi, Xiang Ren

Large language models (LMs) are capable of generating free-text rationales to aid question answering. However, prior work 1) suggests that useful self-rationalization is emergent only at significant scales (e.g., 175B parameter GPT-3); and 2) focuses largely on downstream performance, ignoring the semantics of the rationales themselves, e.g., are they faithful, true, and helpful for humans? In this work, we enable small-scale LMs (∼200x smaller than GPT-3) to generate rationales that not only improve downstream task performance, but are also more plausible, consistent, and diverse, assessed both by automatic and human evaluation. Our method, MaRio (Multi-rewArd RatIOnalization), is a multi-reward conditioned self-rationalization algorithm that optimizes multiple distinct properties like plausibility, diversity and consistency. Results on three difficult question-answering datasets StrategyQA, QuaRel and OpenBookQA show that not only does MaRio improve task accuracy, but it also improves the self-rationalization quality of small LMs across the aforementioned axes better than a supervised fine-tuning (SFT) baseline. Extensive human evaluations confirm that MaRio rationales are preferred vs. SFT rationales, as well as qualitative improvements in plausibility and consistency.

Applications · Language, Speech and Dialog

Longhui Yu, Weisen JIANG, Han Shi, Jincheng YU, Zhengying Liu, Yu Zhang, James Kwok, Zhenguo Li, Adrian Weller, Weiyang Liu

Large language models (LLMs) have pushed the limits of natural language understanding and exhibited excellent problem-solving ability. Despite the great success, most existing open-source LLMs (\eg, LLaMA-2) are still far away from satisfactory for solving mathematical problems due to the complex reasoning procedures. To bridge this gap, we propose \emph{MetaMath}, a finetuned language model that specializes in mathematical reasoning. Specifically, we start by bootstrapping mathematical questions by rewriting the question from multiple perspectives, which results in a new dataset called MetaMathQA. Then we finetune the LLaMA-2 models on MetaMathQA. Experimental results on two popular benchmarks (\ie, GSM8K and MATH) for mathematical reasoning demonstrate that MetaMath outperforms a suite of open-source LLMs by a significant margin. Our MetaMath-7B model achieves $66.5\%$ on GSM8K and $19.8\%$ on MATH, exceeding the state-of-the-art models of the same size by $11.5\%$ and $8.7\%$. Particularly, MetaMath-70B achieves an accuracy of $82.3\%$ on GSM8K, slightly better than GPT-3.5-Turbo. We release the MetaMathQA dataset, the MetaMath models with different model sizes and the training code for public use.

Applications

Qianqian Dong, Zhiying Huang, Qiao Tian, Chen Xu, Tom Ko, yunlong zhao, Siyuan Feng, Tang Li, Kexin Wang, Xuxin Cheng 等

With the huge success of GPT models in natural language processing, there is a growing interest in applying language modeling approaches to speech tasks.Currently, the dominant architecture in speech-to-speech translation (S2ST) remains the encoder-decoder paradigm, creating a need to investigate the impact of language modeling approaches in this area. In this study, we introduce PolyVoice, a language model-based framework designed for S2ST systems. Our framework comprises three decoder-only language models: a translation language model, a duration language model, and a speech synthesis language model. These language models employ different types of prompts to extract learned information effectively. By utilizing unsupervised semantic units, our framework can transfer semantic information across these models, making it applicable even to unwritten languages. We evaluate our system on Chinese $\rightarrow$ English and English $\rightarrow$ Spanish language pairs. Experimental results demonstrate that \method outperforms the state-of-the-art encoder-decoder model, producing voice-cloned speech with high translation and audio quality.Speech samples are available at https://polyvoice.github.io.

Applications · Language, Speech and Dialog

Kang Liu

Taking inspiration from Set Theory, we introduce SetCSE, an innovative information retrieval framework. SetCSE employs sets to represent complex semantics and incorporates well-defined operations for structured information querying under the provided context. Within this framework, we introduce an inter-set contrastive learning objective to enhance comprehension of sentence embedding models concerning the given semantics. Furthermore, we present a suite of operations, including SetCSE intersection, difference, and operation series, that leverage sentence embeddings of the enhanced model for complex sentence retrieval tasks. Throughout this paper, we demonstrate that SetCSE adheres to the conventions of human language expressions regarding compounded semantics, provides a significant enhancement in the discriminatory capability of underlying sentence embedding models, and enables numerous information retrieval tasks involving convoluted and intricate prompts which cannot be achieved using existing querying methods.

Deep Learning · Generative Models and Autoencoders

Yangming Li, Mihaela van der Schaar

Although diffusion models (DMs) have shown promising performances in a number of tasks (e.g., speech synthesis and image generation), they might suffer from error propagation because of their sequential structure. However, this is not certain because some sequential models, such as Conditional Random Field (CRF), are free from this problem. To address this issue, we develop a theoretical framework to mathematically formulate error propagation in the architecture of DMs, The framework contains three elements, including modular error, cumulative error, and propagation equation. The modular and cumulative errors are related by the equation, which interprets that DMs are indeed affected by error propagation. Our theoretical study also suggests that the cumulative error is closely related to the generation quality of DMs. Based on this finding, we apply the cumulative error as a regularization term to reduce error propagation. Because the term is computationally intractable, we derive its upper bound and design a bootstrap algorithm to efficiently estimate the bound for optimization. We have conducted extensive experiments on multiple image datasets, showing that our proposed regularization reduces error propagation, significantly improves vanilla DMs, and outperforms previous baselines.

Yeming Wen, Swarat Chaudhuri

Low-Rank Adaptation (LoRA) has recently gained attention for fine-tuning foundation models by incorporating trainable low-rank matrices, thereby reducing the number of trainable parameters. While \lora/ offers numerous advantages, its applicability for real-time serving to a diverse and global user base is constrained by its incapability to handle multiple task-specific adapters efficiently. This imposes a performance bottleneck in scenarios requiring personalized, task-specific adaptations for each incoming request.To address this, we introduce FLoRA (Fast LoRA), a framework in which each input example in a minibatch can be associated with its unique low-rank adaptation weights, allowing for efficient batching of heterogeneous requests. We empirically demonstrate that \flora/ retains the performance merits of \lora/, showcasing competitive results on the MultiPL-E code generation benchmark spanning over 8 languages and a multilingual speech recognition task across 6 languages.

Applications · Computer Vision

Samar Khanna, Patrick Liu, Linqi Zhou, Chenlin Meng, Robin Rombach, Marshall Burke, David Lobell, Stefano Ermon

Diffusion models have achieved state-of-the-art results on many modalities including images, speech, and video. However, existing models are not tailored to support remote sensing data, which is widely used in important applications including environmental monitoring and crop-yield prediction. Satellite images are significantly different from natural images -- they can be multi-spectral, irregularly sampled across time -- and existing diffusion models trained on images from the Web do not support them. Furthermore, remote sensing data is inherently spatio-temporal, requiring conditional generation tasks not supported by traditional methods based on captions or images. In this paper, we present DiffusionSat, to date the largest generative foundation model trained on a collection of publicly available large, high-resolution remote sensing datasets .As text-based captions are sparsely available for satellite images, we incorporate the associated metadata such as geolocation as conditioning information. Our method produces realistic samples and can be used to solve multiple generative tasks including temporal generation, multi-spectral superrresolution and in-painting. Our method outperforms previous state-of-the-art methods for satellite image generation and is the first large-scale _generative_ foundation model for satellite imagery.The project website can be found here: https://samar-khanna.github.io/DiffusionSat/

Applications · Language, Speech and Dialog

Sreyan Ghosh, Ashish Seth, Sonal Kumar, Utkarsh Tyagi, Chandra Kiran Evuru, Ramaneswaran S, S Sakshi, Oriol Nieto, Ramani Duraiswami, Dinesh Manocha

A fundamental characteristic of audio is its compositional nature. Audio-language models (ALMs) trained using a contrastive approach (e.g., CLAP) that learns a shared representation between audio and language modalities have improved performance in many downstream applications, including zero-shot audio classification, audio retrieval, etc. However, the ability of these models to effectively perform compositional reasoning remains largely unexplored and necessitates additional research. In this paper, we propose CompA, a collection of two expert-annotated benchmarks with a majority of real-world audio samples, to evaluate compositional reasoning in ALMs. Our proposed CompA-order evaluates how well an ALM understands the order or occurrence of acoustic events in audio, and CompA-attribute evaluates attribute-binding of acoustic events. An instance from either benchmark consists of two audio-caption pairs, where both audios have the same acoustic events but with different compositions. An ALM is evaluated on how well it matches the right audio to the right caption. Using this benchmark, we first show that current ALMs perform only marginally better than random chance, thereby struggling with compositional reasoning. Next, we propose CompA-CLAP, where we fine-tune CLAP using a novel learning method to improve its compositional reasoning abilities. To train CompA-CLAP, we first propose improvements to contrastive training with composition-aware hard negatives, allowing for more focused training. Next, we propose a novel modular contrastive loss that helps the model learn fine-grained compositional understanding and overcomes the acute scarcity of openly available compositional audios. CompA-CLAP significantly improves over all our baseline models on the CompA benchmark, indicating its superior compositional reasoning capabilities.