Text-Speech Language Models with Improved Cross-Modal Transfer by Aligning Abstraction Levels

• URL: http://arxiv.org/abs/2503.06211v1
• Date: Sat, 08 Mar 2025 13:28:50 GMT
• Title: Text-Speech Language Models with Improved Cross-Modal Transfer by Aligning Abstraction Levels
• Authors: Santiago Cuervo, Adel Moumen, Yanis Labrak, Sameer Khurana, Antoine Laurent, Mickael Rouvier, Ricard Marxer,
• Abstract summary: We propose augmenting vocabulary expansion with modules that better align abstraction levels across layers.<n>Our models, textscSmolTolk, rival or surpass state-of-the-art TSLMs trained with orders of magnitude more compute.
• Score: 12.179720395334503
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Text-Speech Language Models (TSLMs) -- language models trained to jointly process and generate text and speech -- aim to enable cross-modal knowledge transfer to overcome the scaling limitations of unimodal speech LMs. The predominant approach to TSLM training expands the vocabulary of a pre-trained text LM by appending new embeddings and linear projections for speech, followed by fine-tuning on speech data. We hypothesize that this method limits cross-modal transfer by neglecting feature compositionality, preventing text-learned functions from being fully leveraged at appropriate abstraction levels. To address this, we propose augmenting vocabulary expansion with modules that better align abstraction levels across layers. Our models, \textsc{SmolTolk}, rival or surpass state-of-the-art TSLMs trained with orders of magnitude more compute. Representation analyses and improved multimodal performance suggest our method enhances cross-modal transfer.

Related papers

• TASTE: Text-Aligned Speech Tokenization and Embedding for Spoken Language Modeling [46.60911294356232]
  We introduce Text-Aligned Speech Tokenization and Embedding (TASTE) TASTE is a method that directly addresses the modality gap by aligning speech token with the corresponding text transcription during the tokenization stage. We conduct extensive experiments and show that TASTE can preserve essential paralinguistic information while dramatically reducing the token sequence length.
  arXiv  Detail & Related papers  (2025-04-09T17:14:33Z)
• Adaptive Inner Speech-Text Alignment for LLM-based Speech Translation [20.415410280412697]
  We propose an Adaptive Inner Speech-Text Alignment (AI-STA) method to bridge the modality gap by explicitly aligning speech and text representations at selected layers within large language models (LLMs) Experimental results on speech translation tasks demonstrate that AI-STA significantly improves the translation performance of large speech-text models (LSMs), outperforming previous state-of-the-art approaches.
  arXiv  Detail & Related papers  (2025-03-13T09:54:35Z)
• SparQLe: Speech Queries to Text Translation Through LLMs [0.8901073744693314]
  This study introduces a novel approach that leverages self-supervised speech representations in combination with instruction-tuned LLMs for speech-to-text translation.<n>Our experiments demonstrate that this method effectively preserves the semantic content of the input speech and serves as an effective bridge between self-supervised speech models and instruction-tuned LLMs.
  arXiv  Detail & Related papers  (2025-02-13T12:57:15Z)
• Self-Powered LLM Modality Expansion for Large Speech-Text Models [62.27700381806554]
  Large language models (LLMs) exhibit remarkable performance across diverse tasks. This study aims to refine the use of speech datasets for LSM training by addressing the limitations of vanilla instruction tuning. We introduce a self-powered LSM that leverages augmented automatic speech recognition data generated by the model itself for more effective instruction tuning.
  arXiv  Detail & Related papers  (2024-10-04T04:34:24Z)
• Recent Advances in Speech Language Models: A Survey [45.968078636811356]
  Speech Language Models (SpeechLMs) are end-to-end models that generate speech without converting from text.<n>This survey paper provides the first comprehensive overview of recent methodologies for constructing SpeechLMs.
  arXiv  Detail & Related papers  (2024-10-01T21:48:12Z)
• DeSTA2: Developing Instruction-Following Speech Language Model Without Speech Instruction-Tuning Data [84.01401439030265]
  Recent end-to-end speech language models (SLMs) have expanded upon the capabilities of large language models (LLMs)<n>We present a simple yet effective automatic process for creating speech-text pair data.<n>Our model demonstrates general capabilities for speech-related tasks without the need for speech instruction-tuning data.
  arXiv  Detail & Related papers  (2024-09-30T07:01:21Z)
• VQ-CTAP: Cross-Modal Fine-Grained Sequence Representation Learning for Speech Processing [81.32613443072441]
  For tasks such as text-to-speech (TTS), voice conversion (VC), and automatic speech recognition (ASR), a cross-modal fine-grained (frame-level) sequence representation is desired. We propose a method called Quantized Contrastive Token-Acoustic Pre-training (VQ-CTAP), which uses the cross-modal sequence transcoder to bring text and speech into a joint space.
  arXiv  Detail & Related papers  (2024-08-11T12:24:23Z)
• An End-to-End Speech Summarization Using Large Language Model [7.562198375754054]
  Speech Summarization (SSum) aims to generate human-like text summaries from spoken content. Research on large language models (LLMs) and multimodal information fusion has provided new insights. We propose an end-to-end SSum model that utilizes Q-Former as a connector for the audio-text modality.
  arXiv  Detail & Related papers  (2024-07-02T07:22:57Z)
• SLM: Learning a Discourse Language Representation with Sentence Unshuffling [53.42814722621715]
  We introduce Sentence-level Language Modeling, a new pre-training objective for learning a discourse language representation. We show that this feature of our model improves the performance of the original BERT by large margins.
  arXiv  Detail & Related papers  (2020-10-30T13:33:41Z)
• ST-BERT: Cross-modal Language Model Pre-training For End-to-end Spoken Language Understanding [23.367329217151084]
  We introduce a cross-modal pre-trained language model, called Speech-Text BERT (ST-BERT), to tackle end-to-end spoken language understanding tasks. Taking phoneme posterior and subword-level text as an input, ST-BERT learns a contextualized cross-modal alignment. Our method shows further SLU performance gain via domain-adaptive pre-training with domain-specific speech-text pair data.
  arXiv  Detail & Related papers  (2020-10-23T10:28:20Z)
• SPLAT: Speech-Language Joint Pre-Training for Spoken Language Understanding [61.02342238771685]
  Spoken language understanding requires a model to analyze input acoustic signal to understand its linguistic content and make predictions. Various pre-training methods have been proposed to learn rich representations from large-scale unannotated speech and text. We propose a novel semi-supervised learning framework, SPLAT, to jointly pre-train the speech and language modules.
  arXiv  Detail & Related papers  (2020-10-05T19:29:49Z)
• Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer [64.22926988297685]
  Transfer learning, where a model is first pre-trained on a data-rich task before being fine-tuned on a downstream task, has emerged as a powerful technique in natural language processing (NLP) In this paper, we explore the landscape of introducing transfer learning techniques for NLP by a unified framework that converts all text-based language problems into a text-to-text format.
  arXiv  Detail & Related papers  (2019-10-23T17:37:36Z)

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.