Zero-AVSR: Zero-Shot Audio-Visual Speech Recognition with LLMs by Learning Language-Agnostic Speech Representations

• URL: http://arxiv.org/abs/2503.06273v1
• Date: Sat, 08 Mar 2025 16:40:13 GMT
• Title: Zero-AVSR: Zero-Shot Audio-Visual Speech Recognition with LLMs by Learning Language-Agnostic Speech Representations
• Authors: Jeong Hun Yeo, Minsu Kim, Chae Won Kim, Stavros Petridis, Yong Man Ro,
• Abstract summary: We introduce the Audio-Visual Speech Romanizer (AV-Romanizer), which learns language-agnostic speech representations by predicting Roman text.<n>We convert the predicted Roman text into language-specific graphemes, forming the proposed Cascaded Zero-AVSR.<n>To capture the wide spectrum of phonetic and linguistic diversity, we also introduce a Multilingual Audio-Visual Romanized Corpus (MARC)
• Score: 65.59784436914548
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We explore a novel zero-shot Audio-Visual Speech Recognition (AVSR) framework, dubbed Zero-AVSR, which enables speech recognition in target languages without requiring any audio-visual speech data in those languages. Specifically, we introduce the Audio-Visual Speech Romanizer (AV-Romanizer), which learns language-agnostic speech representations by predicting Roman text. Then, by leveraging the strong multilingual modeling capabilities of Large Language Models (LLMs), we propose converting the predicted Roman text into language-specific graphemes, forming the proposed Cascaded Zero-AVSR. Taking it a step further, we explore a unified Zero-AVSR approach by directly integrating the audio-visual speech representations encoded by the AV-Romanizer into the LLM. This is achieved through finetuning the adapter and the LLM using our proposed multi-task learning scheme. To capture the wide spectrum of phonetic and linguistic diversity, we also introduce a Multilingual Audio-Visual Romanized Corpus (MARC) consisting of 2,916 hours of audio-visual speech data across 82 languages, along with transcriptions in both language-specific graphemes and Roman text. Extensive analysis and experiments confirm that the proposed Zero-AVSR framework has the potential to expand language support beyond the languages seen during the training of the AV-Romanizer.

Related papers

• Zero-resource Speech Translation and Recognition with LLMs [38.11535502039386]
  We propose to leverage a multilingual Large Language Model (LLM) to perform ST and ASR in languages for which the model has never seen paired audio-text data.<n>We achieve this by using a pre-trained multilingual speech encoder, a multilingual LLM, and a lightweight adaptation module that maps the audio representations to the token embedding space of the LLM.
  arXiv  Detail & Related papers  (2024-12-24T17:37:11Z)
• Do Audio-Language Models Understand Linguistic Variations? [42.17718387132912]
  Open-vocabulary audio language models (ALMs) represent a promising new paradigm for audio-text retrieval using natural language queries.<n>We propose RobustCLAP, a novel and compute-efficient technique to learn audio-language representations to linguistic variations.
  arXiv  Detail & Related papers  (2024-10-21T20:55:33Z)
• Efficient Training for Multilingual Visual Speech Recognition: Pre-training with Discretized Visual Speech Representation [55.15299351110525]
  This paper explores sentence-level multilingual Visual Speech Recognition (VSR) that can recognize different languages with a single trained model. We propose a novel training strategy, processing with visual speech units. We set new state-of-the-art multilingual VSR performances by achieving comparable performances to the previous language-specific VSR models.
  arXiv  Detail & Related papers  (2024-01-18T08:46:02Z)
• AudioPaLM: A Large Language Model That Can Speak and Listen [79.44757696533709]
  We introduce AudioPaLM, a large language model for speech understanding and generation. AudioPaLM fuses text-based and speech-based language models. It can process and generate text and speech with applications including speech recognition and speech-to-speech translation.
  arXiv  Detail & Related papers  (2023-06-22T14:37:54Z)
• Speak Foreign Languages with Your Own Voice: Cross-Lingual Neural Codec Language Modeling [92.55131711064935]
  We propose a cross-lingual neural language model, VALL-E X, for cross-lingual speech synthesis. VALL-E X inherits strong in-context learning capabilities and can be applied for zero-shot cross-lingual text-to-speech synthesis and zero-shot speech-to-speech translation tasks. It can generate high-quality speech in the target language via just one speech utterance in the source language as a prompt while preserving the unseen speaker's voice, emotion, and acoustic environment.
  arXiv  Detail & Related papers  (2023-03-07T14:31:55Z)
• ERNIE-SAT: Speech and Text Joint Pretraining for Cross-Lingual Multi-Speaker Text-to-Speech [58.93395189153713]
  We extend the pretraining method for cross-lingual multi-speaker speech synthesis tasks. We propose a speech-text joint pretraining framework, where we randomly mask the spectrogram and the phonemes. Our model shows great improvements over speaker-embedding-based multi-speaker TTS methods.
  arXiv  Detail & Related papers  (2022-11-07T13:35:16Z)
• LAE: Language-Aware Encoder for Monolingual and Multilingual ASR [87.74794847245536]
  A novel language-aware encoder (LAE) architecture is proposed to handle both situations by disentangling language-specific information. Experiments conducted on Mandarin-English code-switched speech suggest that the proposed LAE is capable of discriminating different languages in frame-level.
  arXiv  Detail & Related papers  (2022-06-05T04:03:12Z)
• SAMU-XLSR: Semantically-Aligned Multimodal Utterance-level Cross-Lingual Speech Representation [11.552745999302905]
  We propose the SAMU-XLSR: Semantically-Aligned Multimodal Utterance-level Cross-Lingual Speech Representation learning framework. We combine state-of-the-art multilingual acoustic frame-level speech representation learning model XLS-R with the Language Agnostic BERT Sentence Embedding (LaBSE) model to create an utterance-level multimodal multilingual speech encoder SAMU-XLSR.
  arXiv  Detail & Related papers  (2022-05-17T08:58:48Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.