论文检索

Siqi Li, Danni Liu, Jan Niehues

Direct speech translation (ST) models often struggle with rare words. Incorrect translation of these words can have severe consequences, impacting translation quality and user trust. While rare word translation is inherently challenging for neural models due to sparse learning signals, real-world scenarios often allow access to translations of past recordings on similar topics. To leverage these valuable resources, we propose a retrieval-and-demonstration approach to enhance rare word translation accuracy in direct ST models. First, we adapt existing ST models to incorporate retrieved examples for rare word translation, which allows the model to benefit from prepended examples, similar to in-context learning. We then develop a cross-modal (speech-to-speech, speech-to-text, text-to-text) retriever to locate suitable examples. We demonstrate that standard ST models can be effectively adapted to leverage examples for rare word translation, improving rare word translation accuracy over the baseline by 17.6% with gold examples and 8.5% with retrieved examples. Moreover, our speech-to-speech retrieval approach outperforms other modalities and exhibits higher robustness to unseen speakers. Our code is publicly available.

Tengfei Yu, Xuebo Liu, Zhiyi Hou, Liang Ding, Dacheng Tao, Min Zhang

Large language models (LLMs) exhibit remarkable performance across diverse tasks, indicating their potential for expansion into large speech-text models (LSMs) by integrating speech capabilities. Although unified speech-text pre-training and multimodal data instruction-tuning offer considerable benefits, these methods generally entail significant resource demands and tend to overfit specific tasks.This study aims to refine the use of speech datasets for LSM training by addressing the limitations of vanilla instruction tuning. We explore the instruction-following dynamics within LSMs, identifying a critical issue termed speech anchor bias—a tendency for LSMs to over-rely on speech inputs, mistakenly interpreting the entire speech modality as directives, thereby neglecting textual instructions.To counteract this bias, we introduce a self-powered LSM that leverages augmented automatic speech recognition data generated by the model itself for more effective instruction tuning. Our experiments across a range of speech-based tasks demonstrate that self-powered LSM mitigates speech anchor bias and improves the fusion of speech and text modalities in LSMs. Data, code and scripts are freely available at https://github.com/ytf-philp/Self-powered-LSM.

Liang Zhang, Zhen Yang, Biao Fu, Ziyao Lu, Liangying Shao, Shiyu Liu, Fandong Meng, Jie Zhou, Xiaoli Wang, Jinsong Su

Speech Relation Extraction (SpeechRE) aims to extract relation triplets from speech data. However, existing studies usually use synthetic speech to train and evaluate SpeechRE models, hindering the further development of SpeechRE due to the disparity between synthetic and real speech. Meanwhile, the modality gap issue, unexplored in SpeechRE, limits the performance of existing models. In this paper, we construct two real SpeechRE datasets to facilitate subsequent researches and propose a Multi-level Cross-modal Alignment Model (MCAM) for SpeechRE. Our model consists of three components: 1) a speech encoder, extracting speech features from the input speech; 2) an alignment adapter, mapping these speech features into a suitable semantic space for the text decoder; and 3) a text decoder, autoregressively generating relation triplets based on the speech features. During training, we first additionally introduce a text encoder to serve as a semantic bridge between the speech encoder and the text decoder, and then train the alignment adapter to align the output features of speech and text encoders at multiple levels. In this way, we can effectively train the alignment adapter to bridge the modality gap between the speech encoder and the text decoder. Experimental results and in-depth analysis on our datasets strongly demonstrate the efficacy of our method.

Belen Alastruey, Gerard I. Gállego, Marta R. Costa-jussà

Direct speech-to-text translation systems encounter an important drawback in data scarcity. A common solution consists on pretraining the encoder on automatic speech recognition, hence losing efficiency in the training process. In this study, we compare the training dynamics of a system using a pretrained encoder, the conventional approach, and one trained from scratch. We observe that, throughout the training, the randomly initialized model struggles to incorporate information from the speech inputs for its predictions. Hence, we hypothesize that this issue stems from the difficulty of effectively training an encoder for direct speech translation. While a model trained from scratch needs to learn acoustic and semantic modeling simultaneously, a pretrained one can just focus on the latter. Based on these findings, we propose a subtle change in the decoder cross-attention to integrate source information from earlier steps in training. We show that with this change, the model trained from scratch can achieve comparable performance to the pretrained one, while reducing the training time.

Sougata Saha, Rohini Srihari

The proliferation of online misinformation presents a significant challenge, requiring scalable strategies for effective mitigation. While detection methods exist, current reactive approaches, like content flagging and banning, are short-term and insufficient. Additionally, advancements like large language models (LLMs) exacerbate the issue by enabling large-scale creation and dissemination of misinformation. Thus, sustainable, scalable solutions that encourage behavior change and broaden perspectives by persuading misinformants against their viewpoints or broadening their perspectives are needed. To this end, we propose persuasive LLM-based dialogue systems to tackle misinformation. However, challenges arise due to the lack of suitable datasets and formal frameworks for generating persuasive responses. Inspired by existing methods for countering online hate speech, we explore adapting counter-hate response strategies for misinformation. Since misinformation and hate speech often coexist despite differing intentions, we develop classifiers to identify and annotate response strategies from hate-speech counter-responses for use in misinformation scenarios. Human evaluations show a 91% agreement on the applicability of these strategies to misinformation. Next, as a scalable counter-misinformation solution, we create an LLM-based argument graph framework that generates persuasive responses, using the strategies as control codes to adjust the style and content. Human evaluations and case studies demonstrate that our framework generates expert-like responses and is 14% more engaging, 21% more natural, and 18% more factual than the best available alternatives.

Hao Yang, Lizhen Qu, Ehsan Shareghi, Reza Haf

Large Multimodal Models (LMMs) have achieved great success recently, demonstrating a strong capability to understand multimodal information and to interact with human users. Despite the progress made, the challenge of detecting high-risk interactions in multimodal settings, and in particular in speech modality, remains largely unexplored. Conventional research on risk for speech modality primarily emphasises the content (e.g., what is captured as transcription). However, in speech-based interactions, paralinguistic cues in audio can significantly alter the intended meaning behind utterances. In this work, we propose a speech-specific risk taxonomy, covering 8 risk categories under hostility (malicious sarcasm and threats), malicious imitation (age, gender, ethnicity), and stereotypical biases (age, gender, ethnicity). Based on the taxonomy, we create a small-scale dataset for evaluating current LMMs capability in detecting these categories of risk. We observe even the latest models remain ineffective to detect various paralinguistic-specific risks in speech (e.g., Gemini 1.5 Pro is performing only slightly above random baseline). Warning: this paper contains biased and offensive examples.

Kavya Manohar, Leena G Pillai

This paper explores the pitfalls in evaluating multilingual automatic speech recognition (ASR) models, with a particular focus on Indic language scripts. We investigate the text normalization routine employed by leading ASR models, including OpenAI Whisper, Meta’s MMS, Seamless, and Assembly AI’s Conformer, and their unintended consequences on performance metrics. Our research reveals that current text normalization practices, while aiming to standardize ASR outputs for fair comparison, by removing inconsistencies such as variations in spelling, punctuation, and special characters, are fundamentally flawed when applied to Indic scripts. Through empirical analysis using text similarity scores and in-depth linguistic examination, we demonstrate that these flaws lead to artificially improved performance metrics for Indic languages. We conclude by proposing a shift towards developing text normalization routines that leverage native linguistic expertise, ensuring more robust and accurate evaluations of multilingual ASR models.

Jupinder Parmar, Shrimai Prabhumoye, Joseph Jennings, Bo Liu, Aastha Jhunjhunwala, Zhilin Wang, Mostofa Patwary, Mohammad Shoeybi, Bryan Catanzaro

The impressive capabilities of recent language models can be largely attributed to the multi-trillion token pretraining datasets that they are trained on. However, model developers fail to disclose their construction methodology which has lead to a lack of open information on how to develop effective pretraining sets. To address this issue, we perform the first systematic study across the entire pipeline of pretraining set construction. First, we run ablations on existing techniques for pretraining set development to identify which methods translate to the largest gains in model accuracy on downstream evaluations. Then, we categorize the most widely used data source, web crawl snapshots, across the attributes of toxicity, quality, type of speech, and domain. Finally, we show how such attribute information can be used to further refine and improve the quality of a pretraining set. These findings constitute an actionable set of steps that practitioners can use to develop high quality pretraining sets.

Hyundong Justin Cho, Nicolaas Paul Jedema, Leonardo F. R. Ribeiro, Karishma Sharma, Pedro Szekely, Alessandro Moschitti, Ruben Janssen, Jonathan May

Current instruction-tuned language models are exclusively trained with textual preference data and thus may not be aligned to the unique requirements of other modalities, such as speech. To better align language models with the speech domain, we explore i) prompting strategies based on radio-industry best practices and ii) preference learning using a novel speech-based preference data of 20K samples collected by annotators who listen to response pairs. Both human and automatic evaluation show that both prompting and preference learning increase the speech-suitability of popular instruction tuned LLMs. More interestingly, we show that these methods are additive; combining them achieves the best win rates in head-to-head comparison, resulting in responses that are preferred or tied to the base model in 76.2% of comparisons on average. Lastly, we share lexical, syntactical, and qualitative analyses that elicit how our studied methods differ with baselines in generating more speech-suitable responses.

Yu Tong, Ge Chen, Guokai Zheng, Rui Li, Jiang Dazhi

The current framework for sequence labeling encompasses a feature extractor and a sequence tagger. This study introduces a unified framework named SLGAN, which harnesses the capabilities of Generative Adversarial Networks to address the challenges associated with Sequence Labeling tasks. SLGAN not only mitigates the limitation of GANs in backpropagating loss to discrete data but also exhibits strong adaptability to various sequence labeling tasks. Unlike traditional GANs, the discriminator within SLGAN does not discriminate whether data originates from the discriminator or the generator; instead, it focuses on predicting the correctness of each tag within the tag sequence. We conducted evaluations on six different tasks spanning four languages, including Chinese, Japanese, and Korean Word Segmentation, Chinese and English Named Entity Recognition, and Chinese Part-of-Speech Tagging. Our experimental results illustrate that SLGAN represents a versatile and highly effective solution, consistently achieving state-of-the-art or competitive performance results, irrespective of the specific task or language under consideration.

Simran Khanuja, Sathyanarayanan Ramamoorthy, Yueqi Song, Graham Neubig

Given the rise of multimedia content, human translators increasingly focus on culturally adapting not only words but also other modalities such as images to convey the same meaning. While several applications stand to benefit from this, machine translation systems remain confined to dealing with language in speech and text. In this work, we introduce a new task of translating images to make them culturally relevant. First, we build three pipelines comprising state-of-the-art generative models to do the task. Next, we build a two-part evaluation dataset – (i) concept: comprising 600 images that are cross-culturally coherent, focusing on a single concept per image; and (ii) application: comprising 100 images curated from real-world applications. We conduct a multi-faceted human evaluation of translated images to assess for cultural relevance and meaning preservation. We find that as of today, image-editing models fail at this task, but can be improved by leveraging LLMs and retrievers in the loop. Best pipelines can only translate 5% of images for some countries in the easier concept dataset and no translation is successful for some countries in the application dataset, highlighting the challenging nature of the task. Our project webpage is here: https://machine-transcreation.github.io/image-transcreation and our code, data and model outputs can be found here: https://github.com/simran-khanuja/image-transcreation.

William Chen, Wangyou Zhang, Yifan Peng, Xinjian Li, Jinchuan Tian, Jiatong Shi, Xuankai Chang, Soumi Maiti, Karen Livescu, Shinji Watanabe

Self-supervised learning (SSL) has helped extend speech technologies to more languages by reducing the need for labeled data. However, models are still far from supporting the world’s 7000+ languages. We propose XEUS, a Cross-lingual Encoder for Universal Speech, trained on over 1 million hours of data across 4057 languages, extending the language coverage of SSL models 4-fold. We combine 1 million hours of speech from existing publicly accessible corpora with a newly created corpus of 7400+ hours from 4057 languages, which will be publicly released. To handle the diverse conditions of multilingual speech data, we augment the typical SSL masked prediction approach with a novel dereverberation objective, increasing robustness. We evaluate XEUS on several benchmarks, and show that it consistently outperforms or achieves comparable results to state-of-the-art (SOTA) SSL models across a variety of tasks. XEUS sets a new SOTA on the ML-SUPERB benchmark: it outperforms MMS 1B and w2v-BERT 2.0 v2 by 0.8% and 4.4% respectively, despite having less parameters or pre-training data. Checkpoints, code, and data are found in https://www.wavlab.org/activities/2024/xeus/.

Yuzhe Gu, Enmao Diao

Neural speech codecs aim to compress input signals into minimal bits while maintaining content quality in a low-latency manner. However, existing neural codecs often trade model complexity for reconstruction performance. These codecs primarily use convolutional blocks for feature transformation, which are not inherently suited for capturing the local redundancies in speech signals. To compensate, they require either adversarial discriminators or a large number of model parameters to enhance audio quality. In response to these challenges, we introduce the Efficient Speech Codec (ESC), a lightweight, parameter-efficient speech codec based on a cross-scale residual vector quantization scheme and transformers. Our model employs mirrored hierarchical window transformer blocks and performs step-wise decoding from coarse-to-fine feature representations. To enhance bitrate efficiency, we propose a novel combination of vector quantization techniques along with a pre-training paradigm. Extensive experiments demonstrate that ESC can achieve high-fidelity speech reconstruction with significantly lower model complexity, making it a promising alternative to existing convolutional audio codecs.

Hsuan Su, Hua Farn, Fan-Yun Sun, Shang-Tse Chen, Hung-yi Lee

Synthetic data is widely used in speech recognition due to the availability of text-to-speech models, which facilitate adapting models to previously unseen text domains. However, existing methods suffer in performance when they fine-tune an automatic speech recognition (ASR) model on synthetic data as they suffer from the distributional shift commonly referred to as the synthetic-to-real gap. In this paper, we find that task arithmetic is effective at mitigating this gap. Our proposed method, SYN2REAL task vector, shows an average improvement of 10.03% improvement in word error rate over baselines on the SLURP dataset. Additionally, we show that an average of SYN2REAL task vectors, when we have real speeches from multiple different domains, can further adapt the original ASR model to perform better on the target text domain.

Haozhe Chen, Run Chen, Julia Hirschberg

While recent advances in Text-to-Speech (TTS) technology produce natural and expressive speech, they lack the option for users to select emotion and control intensity. We propose EmoKnob, a framework that allows fine-grained emotion control in speech synthesis with few-shot demonstrative samples of arbitrary emotion. Our framework leverages the expressive speaker representation space made possible by recent advances in foundation voice cloning models. Based on the few-shot capability of our emotion control framework, we propose two methods to apply emotion control on emotions described by open-ended text, enabling an intuitive interface for controlling a diverse array of nuanced emotions. To facilitate a more systematic emotional speech synthesis field, we introduce a set of evaluation metrics designed to rigorously assess the faithfulness and recognizability of emotion control frameworks. Through objective and subjective evaluations, we show that our emotion control framework effectively embeds emotions into speech and surpasses emotion expressiveness of commercial TTS services.

Ming Shan Hee, Aditi Kumaresan, Roy Ka-Wei Lee

The widespread presence of hate speech on the internet, including formats such as text-based tweets and multimodal memes, poses a significant challenge to digital platform safety. Recent research has developed detection models tailored to specific modalities; however, there is a notable gap in transferring detection capabilities across different formats. This study conducts extensive experiments using few-shot in-context learning with large language models to explore the transferability of hate speech detection between modalities. Our findings demonstrate that text-based hate speech examples can significantly enhance the classification accuracy of vision-language hate speech. Moreover, text-based demonstrations outperform vision-language demonstrations in few-shot learning settings. These results highlight the effectiveness of cross-modality knowledge transfer and offer valuable insights for improving hate speech detection systems.

Vyas Raina, Rao Ma, Charles McGhee, Kate Knill, Mark Gales

该来源暂未提供摘要。

Nguyen Van Dinh, Thanh Chi Dang, Luan Thanh Nguyen, Kiet Van Nguyen

Vietnamese, a low-resource language, is typically categorized into three primary dialect groups that belong to Northern, Central, and Southern Vietnam. However, each province within these regions exhibits its own distinct pronunciation variations. Despite the existence of various speech recognition datasets, none of them has provided a fine-grained classification of the 63 dialects specific to individual provinces of Vietnam. To address this gap, we introduce Vietnamese Multi-Dialect (ViMD) dataset, a novel comprehensive dataset capturing the rich diversity of 63 provincial dialects spoken across Vietnam. Our dataset comprises 102.56 hours of audio, consisting of approximately 19,000 utterances, and the associated transcripts contain over 1.2 million words. To provide benchmarks and simultaneously demonstrate the challenges of our dataset, we fine-tune state-of-the-art pre-trained models for two downstream tasks: (1) Dialect identification and (2) Speech recognition. The empirical results suggest two implications including the influence of geographical factors on dialects, and the constraints of current approaches in speech recognition tasks involving multi-dialect speech data. Our dataset is available for research purposes.

Jindřich Libovický, Jindřich Helcl

We present three innovations in tokenization and subword segmentation. First, we propose to use unsupervised morphological analysis with Morfessor as pre-tokenization. Second, we present an algebraic method for obtaining subword embeddings grounded in a word embedding space. Based on that, we design a novel subword segmentation algorithm that uses the embeddings, ensuring that the procedure considers lexical meaning. Third, we introduce an efficient segmentation algorithm based on a subword bigram model that can be initialized with the lexically aware segmentation method to avoid using Morfessor and large embedding tables at inference time. We evaluate the proposed approaches using two intrinsic metrics and measure their performance on two downstream tasks: part-of-speech tagging and machine translation. Our experiments show significant improvements in the morphological plausibility of the segmentation when evaluated using segmentation precision on morpheme boundaries and improved Rényi efficiency in 8 languages. Although the proposed tokenization methods do not have a large impact on automatic translation quality, we observe consistent performance gains in the arguably more morphological task of part-of-speech tagging.

Hongfu Liu, Hengguan Huang, Ye Wang

Acoustic foundation models, fine-tuned for Automatic Speech Recognition (ASR), suffer from performance degradation in wild acoustic test settings when deployed in real-world scenarios. Stabilizing online Test-Time Adaptation (TTA) under these conditions remains an open and unexplored question. Existing wild vision TTA methods often fail to handle speech data effectively due to the unique characteristics of high-entropy speech frames, which are unreliably filtered out even when containing crucial semantic content. Furthermore, unlike static vision data, speech signals follow short-term consistency, requiring specialized adaptation strategies. In this work, we propose a novel wild acoustic TTA method tailored for ASR fine-tuned acoustic foundation models. Our method, Confidence-Enhanced Adaptation, performs frame-level adaptation using a confidence-aware weight scheme to avoid filtering out essential information in high-entropy frames. Additionally, we apply consistency regularization during test-time optimization to leverage the inherent short-term consistency of speech signals. Our experiments on both synthetic and real-world datasets demonstrate that our approach outperforms existing baselines under various wild acoustic test settings, including Gaussian noise, environmental sounds, accent variations, and sung speech.