Prepending or Cross-Attention for Speech-to-Text? An Empirical Comparison

• URL: http://arxiv.org/abs/2501.02370v3
• Date: Fri, 07 Feb 2025 20:12:12 GMT
• Title: Prepending or Cross-Attention for Speech-to-Text? An Empirical Comparison
• Authors: Tsz Kin Lam, Marco Gaido, Sara Papi, Luisa Bentivogli, Barry Haddow,
• Abstract summary: We compare the performance of dense feature prepending (DFP) and cross-attention architecture. Despite the wide adoption of DFP, our results do not indicate a clear advantage of DFP over cross-attention.
• Score: 27.44915531637358
• License:
• Abstract: Following the remarkable success of Large Language Models (LLMs) in NLP tasks, there is increasing interest in extending their capabilities to speech -- the most common form of communication. The most widespread approach to integrating speech into LLMs is dense feature prepending (DFP), which prepends the projected speech representations to the textual representations, allowing end-to-end training with a speech encoder. This raises questions about the need for a sophisticated speech encoder for DFP and how its performance compares with a standard encoder-decoder (i.e., cross-attention) architecture. We compare DFP and cross-attention under a variety of configurations, such as CTC compression, sequence-level knowledge distillation, on monolingual, bilingual, and multilingual models. To perform a controlled architectural comparison, we train all models from scratch rather than using large pretrained models and use comparable data and parameter settings, testing speech-to-text recognition (ASR) and translation (ST) on MuST-C v1.0 and CoVoST2 datasets. Despite the wide adoption of DFP, our results do not indicate a clear advantage of DFP over cross-attention.

Related papers

• Advancing Multi-talker ASR Performance with Large Language Models [48.52252970956368]
  Recognizing overlapping speech from multiple speakers in conversational scenarios is one of the most challenging problem for automatic speech recognition (ASR) In this paper, we propose an LLM-based SOT approach for multi-talker ASR, leveraging pre-trained speech encoder and LLM. Our approach surpasses traditional AED-based methods on the simulated dataset LibriMix and achieves state-of-the-art performance on the evaluation set of the real-world dataset AMI.
  arXiv  Detail & Related papers  (2024-08-30T17:29:25Z)
• Investigating Decoder-only Large Language Models for Speech-to-text Translation [39.17113782374464]
  Large language models (LLMs) are known for their exceptional reasoning capabilities, generalizability, and fluency across diverse domains. We propose a decoder-only architecture that enables the LLM to directly consume the encoded speech representation and generate the text translation. Our model achieves state-of-the-art performance on CoVoST 2 and FLEURS among models trained without proprietary data.
  arXiv  Detail & Related papers  (2024-07-03T14:42:49Z)
• DiscreteSLU: A Large Language Model with Self-Supervised Discrete Speech Units for Spoken Language Understanding [51.32965203977845]
  We propose the use of discrete speech units (DSU) instead of continuous-valued speech encoder outputs. The proposed model shows robust performance on speech inputs from seen/unseen domains and instruction-following capability in spoken question answering. Our findings suggest that the ASR task and datasets are not crucial in instruction-tuning for spoken question answering tasks.
  arXiv  Detail & Related papers  (2024-06-13T17:28:13Z)
• The Interpreter Understands Your Meaning: End-to-end Spoken Language Understanding Aided by Speech Translation [13.352795145385645]
  Speech translation (ST) is a good means of pretraining speech models for end-to-end spoken language understanding. We show that our models reach higher performance over baselines on monolingual and multilingual intent classification. We also create new benchmark datasets for speech summarization and low-resource/zero-shot transfer from English to French or Spanish.
  arXiv  Detail & Related papers  (2023-05-16T17:53:03Z)
• Bidirectional Representations for Low Resource Spoken Language Understanding [39.208462511430554]
  We propose a representation model to encode speech in bidirectional rich encodings. The approach uses a masked language modelling objective to learn the representations. We show that the performance of the resulting encodings is better than comparable models on multiple datasets.
  arXiv  Detail & Related papers  (2022-11-24T17:05:16Z)
• SpeechUT: Bridging Speech and Text with Hidden-Unit for Encoder-Decoder Based Speech-Text Pre-training [106.34112664893622]
  We propose a unified-modal speech-unit-text pre-training model, SpeechUT, to connect the representations of a speech encoder and a text decoder with a shared unit encoder. Our proposed SpeechUT is fine-tuned and evaluated on automatic speech recognition (ASR) and speech translation (ST) tasks.
  arXiv  Detail & Related papers  (2022-10-07T17:57:45Z)
• Enhanced Direct Speech-to-Speech Translation Using Self-supervised Pre-training and Data Augmentation [76.13334392868208]
  Direct speech-to-speech translation (S2ST) models suffer from data scarcity issues. In this work, we explore self-supervised pre-training with unlabeled speech data and data augmentation to tackle this issue.
  arXiv  Detail & Related papers  (2022-04-06T17:59:22Z)
• RealTranS: End-to-End Simultaneous Speech Translation with Convolutional Weighted-Shrinking Transformer [33.876412404781846]
  RealTranS is an end-to-end model for simultaneous speech translation. It maps speech features into text space with a weighted-shrinking operation and a semantic encoder. Experiments show that RealTranS with the Wait-K-Stride-N strategy outperforms prior end-to-end models.
  arXiv  Detail & Related papers  (2021-06-09T06:35:46Z)
• Dual-decoder Transformer for Joint Automatic Speech Recognition and Multilingual Speech Translation [71.54816893482457]
  We introduce dual-decoder Transformer, a new model architecture that jointly performs automatic speech recognition (ASR) and multilingual speech translation (ST) Our models are based on the original Transformer architecture but consist of two decoders, each responsible for one task (ASR or ST)
  arXiv  Detail & Related papers  (2020-11-02T04:59:50Z)
• 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)

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.