论文检索

Applications · Language, Speech and Dialog

Zhengrui Ma, Yang Feng, Min zhang

Streaming generation models are utilized across fields, with the Transducer architecture being popular in industrial applications. However, its input-synchronous decoding mechanism presents challenges in tasks requiring non-monotonic alignments, such as simultaneous translation. In this research, we address this issue by integrating Transducer's decoding with the history of input stream via a learnable monotonic attention. Our approach leverages the forward-backward algorithm to infer the posterior probability of alignments between the predictor states and input timestamps, which is then used to estimate the monotonic context representations, thereby avoiding the need to enumerate the exponentially large alignment space during training. Extensive experiments show that our MonoAttn-Transducer effectively handles non-monotonic alignments in streaming scenarios, offering a robust solution for complex generation tasks. Code is available at https://github.com/ictnlp/MonoAttn-Transducer.

Applications · Language, Speech and Dialog

Chuheng Zhang, Wei Shen, Li Zhao, Xuyun Zhang, Xiaolong Xu, Wanchun Dou, Jiang Bian

While direct policy optimization methods exist, pioneering LLMs are fine-tuned with reinforcement learning from human feedback (RLHF) to generate better responses under the supervision of a reward model learned from preference data. One major challenge of RLHF is the inaccuracy of the intermediate reward model, especially in the tasks that requires complex reasoning for the reward model to score a response. We find that the reliability of the reward model varies across responses assigned with different rewards. This motivates us to filter the samples whose rewards may be unreliable to improve the signal-to-noise ratio during policy learning, resulting in Policy Filtration for Proximal Policy Optimization (PF-PPO). To choose a proper policy filtering strategy, we use the coefficient of determination ($R^2$) between the rewards and actual scores on filtered samples as the metrics to help us find promising strategies since it measures how well the rewards filtered by PF-PPO indicate real performance. We provide extensive experiments to validate the effectiveness of PF-PPO in code generation and math reasoning tasks. In code generation, PF-PPO achieves the state-of-the-art performance of 7-billion-parameter models on HumanEval (+7.9%), MBPP (+0.7%), and LeetCode Contest (+10.0%) which is a more challenging benchmark created by us. In math reasoning, PF-PPO yields performance increase using different reward models and benchmarks (Ape210K and CMATH).

Applications · Language, Speech and Dialog

Sungnyun Kim, Kangwook Jang, Sangmin Bae, Sungwoo Cho, Se-Young Yun

Audio-visual speech recognition (AVSR) has become critical for enhancing speech recognition in noisy environments by integrating both auditory and visual modalities. However, existing AVSR systems struggle to scale up without compromising computational efficiency. In this study, we introduce MoHAVE (Mixture of Hierarchical Audio-Visual Experts), a novel robust AVSR framework designed to address these scalability constraints. By leveraging a Mixture-of-Experts (MoE) architecture, MoHAVE activates modality-specific expert groups, ensuring dynamic adaptation to various audio-visual inputs with minimal computational overhead. Key contributions of MoHAVE include: (1) a sparse MoE framework that efficiently scales AVSR model capacity, (2) a hierarchical gating mechanism that dynamically utilizes the expert groups based on input context, enhancing adaptability and robustness, and (3) remarkable performance across robust AVSR benchmarks, including LRS3 and MuAViC transcription and translation tasks, setting a new standard for scalable speech recognition systems.

Deep Learning · Other Representation Learning

Dianwen Ng, Kun Zhou, Yi-Wen Chao, Zhiwei Xiong, Bin Ma, EngSiong Chng

Achieving high-fidelity audio compression while preserving perceptual quality across diverse audio types remains a significant challenge in Neural Audio Coding (NAC). This paper introduces MUFFIN, a fully convolutional NAC framework that leverages psychoacoustically guided multi-band frequency reconstruction. Central to MUFFIN is the Multi-Band Spectral Residual Vector Quantization (MBS-RVQ) mechanism, which quantizes latent speech across different frequency bands. This approach optimizes bitrate allocation and enhances fidelity based on psychoacoustic studies, achieving efficient compression with unique perceptual features that separate content from speaker attributes through distinct codebooks. MUFFIN integrates a transformer-inspired convolutional architecture with proposed modified snake activation functions to capture fine frequency details with greater precision. Extensive evaluations on diverse datasets (LibriTTS, IEMOCAP, GTZAN, BBC) demonstrate MUFFIN’s ability to consistently surpass existing performance in audio reconstruction across various domains. Notably, a high-compression variant achieves an impressive SOTA 12.5 kHz rate while preserving reconstruction quality. Furthermore, MUFFIN excels in downstream generative tasks, demonstrating its potential as a robust token representation for integration with large language models. These results establish MUFFIN as a groundbreaking advancement in NAC and as the first neural psychoacoustic coding system. Speech demos and codes are available at \url{https://demos46.github.io/muffin/} and \url{https://github.com/dianwen-ng/MUFFIN}.

Social Aspects · Safety

Taesoo Kim, Jinju Kim, Dongchan Kim, Jong Hwan Ko, Gyeong-Moon Park

The rapid advancement of Zero-Shot Text-to-Speech (ZS-TTS) technology has enabled high-fidelity voice synthesis from minimal audio cues, raising significant privacy and ethical concerns. Despite the threats to voice privacy, research to selectively remove the knowledge to replicate unwanted individual voices from pre-trained model parameters has not been explored. In this paper, we address the new challenge of speaker identity unlearning for ZS-TTS systems. To meet this goal, we propose the first machine unlearning frameworks for ZS-TTS, especially Teacher-Guided Unlearning (TGU), designed to ensure the model forgets designated speaker identities while retaining its ability to generate accurate speech for other speakers. Our proposed methods incorporate randomness to prevent consistent replication of forget speakers' voices, assuring unlearned identities remain untraceable. Additionally, we propose a new evaluation metric, speaker-Zero Retrain Forgetting (spk-ZRF). This assesses the model's ability to disregard prompts associated with forgotten speakers, effectively neutralizing its knowledge of these voices. The experiments conducted on the state-of-the-art model demonstrate that TGU prevents the model from replicating forget speakers' voices while maintaining high quality for other speakers.The demo is available at https://speechunlearn.github.io/ .

Applications · Language, Speech and Dialog

William English, Dominic Simon, Sumit Jha, Rickard Ewetz

Translating natural language (NL) into a formal language such as temporal logic (TL) is integral for human communication with robots and autonomous systems. State-of-the-art approaches decompose the task into a grounding of atomic propositions (APs) phase and a translation phase. However, existing methods struggle with accurate grounding, the existence of co-references, and learning from limited data. In this paper, we propose a framework for NL to TL translation called Grammar Forced Translation (GraFT). The framework is based on the observation that previous work solves both the grounding and translation steps by letting a language model iteratively predict tokens from its full vocabulary. In contrast, GraFT reduces the complexity of both tasks by restricting the set of valid output tokens from the full vocabulary to only a handful in each step. The solution space reduction is obtained by exploiting the unique properties of each problem. We also provide a theoretical justification for why the solution space reduction leads to more efficient learning. We evaluate the effectiveness of GraFT using the CW, GLTL, and Navi benchmarks. Compared with state-of-the-art translation approaches, it can be observed that GraFT improves the end-to-end translation accuracy by 5.49% and out-of-domain translation accuracy by 14.06% on average.

Applications · Language, Speech and Dialog

Lars Klein, Nearchos Potamitis, Roland Aydin, Robert West, Caglar Gulcehre, Akhil Arora

While numerous frameworks have been developed to enhance the reasoning abilities of large language models (LLMs), there is a scarcity of methods that effectively balance the trade-off between cost and quality. In this paper, we introduce Fleet of Agents (FoA), a novel and intuitive yet principled framework utilizing LLMs as agents to navigate through dynamic tree searches, employing a genetic-type particle filtering approach. FoA spawns a multitude of agents, each exploring the search space autonomously, followed by a selection phase where resampling based on a heuristic value function optimizes the balance between exploration and exploitation. This mechanism enables dynamic branching, adapting the exploration strategy based on discovered solutions. We conduct extensive experiments on four benchmark tasks, \``Game of 24\'', \``Mini-Crosswords\'', \``WebShop\'' and \``SciBench\'', utilizing four different LLMs, GPT-3.5, GPT-4, LLaMA3.2-11B, and LLaMA3.2-90B. On average across all tasks and LLMs, FoA obtains an absolute quality improvement of $\simeq 5\%$ while requiring only $\simeq 35\%$ of the cost of previous SOTA methods. Notably, our analyses reveal that (1) FoA achieves the best cost-quality trade-off among all benchmarked methods, and (2) FoA+ LLaMA3.2-11B surpasses the Llama3.2-90B model. FoA is publicly available at [https://github.com/au-clan/FoA](https://github.com/au-clan/FoA).

Position · Methodology

Michael Kirchhof, Gjergji Kasneci, Enkelejda Kasneci

Large-language models (LLMs) and chatbot agents are known to provide wrong outputs at times, and it was recently found that this can never be fully prevented. Hence, uncertainty quantification plays a crucial role, aiming to quantify the level of ambiguity in either one overall number or two numbers for aleatoric and epistemic uncertainty. This position paper argues that this traditional dichotomy of uncertainties is too limited for the open and interactive setup that LLM agents operate in when communicating with a user, and that we need to research avenues that enrich uncertainties in this novel scenario. We review the literature and find that popular definitions of aleatoric and epistemic uncertainties directly contradict each other and lose their meaning in interactive LLM agent settings. Hence, we propose three novel research directions that focus on uncertainties in such human-computer interactions: Underspecification uncertainties, for when users do not provide all information or define the exact task at the first go, interactive learning, to ask follow-up questions and reduce the uncertainty about the current context, and output uncertainties, to utilize the rich language and speech space to express uncertainties as more than mere numbers. We expect that these new ways of dealing with and communicating uncertainties will lead to LLM agent interactions that are more transparent, trustworthy, and intuitive.

Applications · Language, Speech and Dialog

Tom Labiausse, Laurent Mazaré, Edouard Grave, Alexandre Défossez, Neil Zeghidour

We introduce Hibiki, a decoder-only model for simultaneous speech translation. Hibiki leverages a multistream language model to synchronously process source and target speech, and jointly produces text and audio tokens to perform speech-to-text and speech-to-speech translation. We furthermore address the fundamental challenge of simultaneous interpretation, which unlike its consecutive counterpart --where one waits for the end of the source utterance to start translating-- adapts its flow to accumulate just enough context to produce a correct translation in real-time, chunk by chunk. To do so, we introduce a weakly-supervised method that leverages the perplexity of an off-the-shelf text translation system to identify optimal delays on a per-word basis and create aligned synthetic data. After supervised training, Hibiki performs adaptive, simultaneous speech translation with vanilla temperature sampling. On a French-English simultaneous speech translation task, Hibiki demonstrates state-of-the-art performance in translation quality, speaker fidelity and naturalness. Moreover, the simplicity of its inference process makes it compatible with batched translation and even real-time on-device deployment. We provide examples on *huggingface.co/spaces/kyutai/hibiki-samples* as well as models and inference code at *github.com/kyutai-labs/hibiki*.

Applications · Language, Speech and Dialog

Zhongweiyang Xu, Xulin Fan, Zhong-Qiu Wang, Xilin Jiang, Romit Roy Choudhury

Blind Speech Separation (BSS) aims to separate multiple speech sources from audio mixturesrecorded by a microphone array. The problem ischallenging because it is a blind inverse problem,i.e., the microphone array geometry, the room impulse response (RIR), and the speech sources, areall unknown. We propose ArrayDPS to solve theBSS problem in an unsupervised, array-agnostic,and generative manner. The core idea builds ondiffusion posterior sampling (DPS), but unlikeDPS where the likelihood is tractable, ArrayDPSmust approximate the likelihood by formulatinga separate optimization problem. The solution to the optimization approximates room acousticsand the relative transfer functions between microphones. These approximations, along with thediffusion priors, iterate through the ArrayDPSsampling process and ultimately yield separatedvoice sources. We only need a simple single-speaker speech diffusion model as a prior, alongwith the mixtures recorded at the microphones; nomicrophone array information is necessary. Evaluation results show that ArrayDPS outperformsall baseline unsupervised methods while beingcomparable to supervised methods in terms ofSDR. Audio demos and codes are provided at:https://arraydps.github.io/ArrayDPSDemo/ andhttps://github.com/ArrayDPS/ArrayDPS.

Applications · Language, Speech and Dialog

Taejin Park, Ivan Medennikov, Kunal Dhawan, Weiqing Wang, He Huang, Nithin Koluguri, Krishna Puvvada, Jagadeesh Balam, Boris Ginsburg

Sortformer is an encoder-based speaker diarization model designed for supervising speaker tagging in speech-to-text models. Instead of relying solely on permutation invariant loss (PIL), Sortformer introduces Sort Loss to resolve the permutation problem, either independently or in tandem with PIL. In addition, we propose a streamlined multi-speaker speech-to-text architecture that leverages Sortformer for speaker supervision, embedding speaker labels into the encoder using sinusoidal kernel functions. This design addresses the speaker permutation problem through sorted objectives, effectively bridging timestamps and tokens to supervise speaker labels in the output transcriptions. Experiments demonstrate that Sort Loss can boost speaker diarization performance, and incorporating the speaker supervision from Sortformer improves multi-speaker transcription accuracy. We anticipate that the proposed Sortformer and multi-speaker architecture will enable the seamless integration of speaker tagging capabilities into foundational speech-to-text systems and multimodal large language models (LLMs), offering an easily adoptable and user-friendly mechanism to enhance their versatility and performance in speaker-aware tasks. The code and trained models are made publicly available through the NVIDIA NeMo Framework.

Applications · Language, Speech and Dialog

Hao Gu, Wei Li, Lujun Li, Qiyuan Zhu, Mark Lee, Shengjie Sun, Wei Xue, Yike Guo

Mixture-of-Experts (MoE) architectures in large language models (LLMs) achieve exceptional performance, but face prohibitive storage and memory requirements. To address these challenges, we present $D^2$-MoE, a new delta decompression compressor for reducing the parameters of MoE LLMs. Based on observations of expert diversity, we decompose their weights into a shared base weight and unique delta weights. Specifically, our method first merges each expert's weight into the base weight using the Fisher information matrix to capture shared components. Then, we compress delta weights through Singular Value Decomposition (SVD) by exploiting their low-rank properties.Finally, we introduce a semi-dynamical structured pruning strategy for the base weights, combining static and dynamic redundancy analysis to achieve further parameter reduction while maintaining input adaptivity. In this way, our $D^2$-MoE successfully compacts MoE LLMs to high compression ratios without additional training. Extensive experiments highlight the superiority of our approach, with over 13\% performance gains than other compressors on Mixtral|Phi-3.5|DeepSeek|Qwen2 MoE LLMs at 40$\sim$60\% compression rates. Codes are available in https://github.com/lliai/D2MoE.

Applications · Language, Speech and Dialog

Jimmy Wang, Tom Zollo, Richard Zemel, Hongseok Namkoong

Eliciting information to reduce uncertainty about a latent entity is a critical task in many application domains, e.g., assessing individual student learning outcomes, diagnosing underlying diseases, or learning user preferences. Though natural language is a powerful medium for this purpose, large language models (LLMs) and existing fine-tuning algorithms lack mechanisms for strategically gathering information to refine their own understanding of the latent entity. To harness the generalization power and world knowledge of LLMs in developing effective information-gathering strategies, we propose an adaptive elicitation framework that actively reduces uncertainty on the latent entity. Since probabilistic modeling of an abstract latent entity is difficult, our framework adopts a predictive view of uncertainty, using a meta-learned language model to simulate future observations and enable scalable uncertainty quantification over complex natural language. Through autoregressive forward simulation, our model quantifies how new questions reduce epistemic uncertainty, enabling the development of sophisticated information-gathering strategies to choose the most informative next queries. In experiments on the 20 questions game, dynamic opinion polling, and adaptive student assessment, our method consistently outperforms baselines in identifying critical unknowns and improving downstream predictions, illustrating the promise of strategic information gathering in natural language settings.

Deep Learning · Large Language Models

Sreyan Ghosh, Zhifeng Kong, Sonal Kumar, S Sakshi, Jaehyeon Kim, Wei Ping, Rafael Valle, Dinesh Manocha, Bryan Catanzaro

Understanding and reasoning over non-speech sounds and music are crucial for both humans and AI agents to interact effectively with their environments. In this paper, we introduce Audio Flamingo 2 (AF2), an Audio-Language Model (ALM) with advanced audio understanding and reasoning capabilities. AF2 leverages (i) a custom CLAP model, (ii) synthetic Audio QA data for fine-grained audio reasoning, and (iii) a multi-stage curriculum learning strategy. AF2 achieves state-of-the-art performance with only a 3B parameter small language model, surpassing large open-source and proprietary models across over 20 benchmarks. Next, for the first time, we extend audio understanding to long audio segments (30 secs to 5 mins) and propose LongAudio, a large and novel dataset for training ALMs on long audio captioning and question-answering tasks. Fine-tuning AF2 on LongAudio leads to exceptional performance on our proposed LongAudioBench, an expert-annotated benchmark for evaluating ALMs on long audio understanding capabilities. We conduct extensive ablation studies to confirm the efficacy of our approach.

Applications · Language, Speech and Dialog

Martin Andrews, Sam Witteveen

Cryptic crossword clues are challenging language tasks for which new test sets are released daily by major newspapers on a global basis. Each cryptic clue contains both the definition of the answer to be placed in the crossword grid (in common with regular crosswords), and ‘wordplay’ that *proves* that the answer is correct (i.e. a human solver can be confident that an answer is correct without needing crossing words as confirmation). This work describes an LLM-based reasoning system built from open-licensed components that solves cryptic clues by (i) hypothesising answers; (ii) proposing wordplay explanations; and (iii) using a verifier system that operates on codified reasoning steps. Overall, this system establishes a new state-of-the-art performance on the challenging Cryptonite dataset of clues from The Times and The Telegraph newspapers in the UK. Because each proved solution is expressed in Python, interpretable wordplay reasoning for proven answers is available for inspection.

Optimization

Lisha Chen, Quan Xiao, Ellen Fukuda, Xinyi Chen, Kun Yuan, Tianyi Chen

Multi-objective learning under user-specified preference is common in real-world problems such as multi-lingual speech recognition under fairness. In this work, we frame such a problem as a semivectorial bilevel optimization problem, whose goal is to optimize a pre-defined preference function, subject to the constraint that the model parameters are weakly Pareto optimal. To solve this problem, we convert the multi-objective constraints to a single-objective constraint through a merit function with an easy-to-evaluate gradient, and then, we use a penalty-based reformulation of the bilevel optimization problem. We theoretically establish the properties of the merit function, and the relations of solutions for the penalty reformulation and the constrained formulation. Then we propose algorithms to solve the reformulated single-level problem, and establish its convergence guarantees. We test the method on various synthetic and real-world problems. The results demonstrate the effectiveness of the proposed method in finding preference-guided optimal solutions to the multi-objective problem.

Applications · Language, Speech and Dialog

Qichao Wang, Ziqiao Meng, Wenqian Cui, Yifei Zhang, Pengcheng Wu, Bingzhe Wu, Irwin King, Liang Chen, Peilin Zhao

Inspired by the impressive capabilities of GPT-4o, there is growing interest in enabling speech language models (SLMs) to engage in natural, fluid spoken interactions with humans. Recent advancements have led to the development of several SLMs that demonstrate promising results in this area. However, current approaches have yet to fully exploit dual-channel speech data, which inherently captures the structure and dynamics of human conversation. In this work, we systematically explore the use of dual-channel speech data in the context of modern large language models, and introduce a novel generative modeling paradigm—Next-Token-Pair Prediction (NTPP)—to enable speaker-independent dual-channel spoken dialogue learning using decoder-only architectures for the first time. We evaluate our approach on standard benchmarks, and empirical results show that our proposed method, NTPP, significantly improves the conversational abilities of SLMs in terms of turn-taking prediction, response coherence, and naturalness. Moreover, compared to existing methods, NTPP achieves substantially lower inference latency, highlighting its practical efficiency for real-time applications. Demo and code can be found at https://audio-3059.pages.dev.

Applications · Neuroscience, Cognitive Science

Dulhan Jayalath, Gilad Landau, Brendan Shillingford, Mark Woolrich, ʻŌiwi Parker Jones

The past few years have seen remarkable progress in the decoding of speech from brain activity, primarily driven by large single-subject datasets. However, due to individual variation, such as anatomy, and differences in task design and scanning hardware, leveraging data across subjects and datasets remains challenging. In turn, the field has not benefited from the growing number of open neural data repositories to exploit large-scale deep learning. To address this, we develop neuroscience-informed self-supervised objectives, together with an architecture, for learning from heterogeneous brain recordings. Scaling to nearly **400 hours** of MEG data and **900 subjects**, our approach shows generalisation across participants, datasets, tasks, and even to *novel* subjects. It achieves **improvements of 15-27%** over state-of-the-art models and **matches *surgical* decoding performance with *non-invasive* data**. These advances unlock the potential for scaling speech decoding models beyond the current frontier.

Applications · Language, Speech and Dialog

Yinghao Li, Rithesh Kumar, Zeyu Jin

Diffusion models have demonstrated significant potential in speech synthesis tasks, including text-to-speech (TTS) and voice cloning. However, their iterative denoising processes are computationally intensive, and previous distillation attempts have shown consistent quality degradation. Moreover, existing TTS approaches are limited by non-differentiable components or iterative sampling that prevent true end-to-end optimization with perceptual metrics. We introduce DMOSpeech, a distilled diffusion-based TTS model that uniquely achieves both faster inference and superior performance compared to its teacher model. By enabling direct gradient pathways to all model components, we demonstrate the first successful end-to-end optimization of differentiable metrics in TTS, incorporating Connectionist Temporal Classification (CTC) loss and Speaker Verification (SV) loss. Our comprehensive experiments, validated through extensive human evaluation, show significant improvements in naturalness, intelligibility, and speaker similarity while reducing inference time by orders of magnitude. This work establishes a new framework for aligning speech synthesis with human auditory preferences through direct metric optimization. The audio samples are available at https://dmospeech.github.io/demo

Deep Learning · Generative Models and Autoencoders

Jaehyeon Kim, Taehong Moon, Keon Lee, Jaewoong Cho

We introduce ResGen, an efficient Residual Vector Quantization (RVQ)-based generative model for high-fidelity generation with fast sampling. RVQ improves data fidelity by increasing the number of quantization steps, referred to as depth, but deeper quantization typically increases inference steps in generative models. To address this, ResGen directly predicts the vector embedding of collective tokens rather than individual ones, ensuring that inference steps remain independent of RVQ depth. Additionally, we formulate token masking and multi-token prediction within a probabilistic framework using discrete diffusion and variational inference. We validate the efficacy and generalizability of the proposed method on two challenging tasks across different modalities: conditional image generation on ImageNet 256×256 and zero-shot text-to-speech synthesis. Experimental results demonstrate that ResGen outperforms autoregressive counterparts in both tasks, delivering superior performance without compromising sampling speed. Furthermore, as we scale the depth of RVQ, our generative models exhibit enhanced generation fidelity or faster sampling speeds compared to similarly sized baseline models.