Tokenwise Contrastive Pretraining for Finer Speech-to-BERT Alignment in End-to-End Speech-to-Intent Systems

• URL: http://arxiv.org/abs/2204.05188v1
• Date: Mon, 11 Apr 2022 15:24:25 GMT
• Title: Tokenwise Contrastive Pretraining for Finer Speech-to-BERT Alignment in End-to-End Speech-to-Intent Systems
• Authors: Vishal Sunder, Eric Fosler-Lussier, Samuel Thomas, Hong-Kwang J. Kuo, Brian Kingsbury
• Abstract summary: This work is a step towards doing the same in a much more efficient and fine-grained manner where we align speech embeddings and BERT embeddings on a token-by-token basis. We introduce a simple yet novel technique that uses a cross-modal attention mechanism to extract token-level contextual embeddings from a speech encoder. Fine-tuning such a pretrained model to perform intent recognition using speech directly yields state-of-the-art performance on two widely used SLU datasets.
• Score: 31.18865184576272
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent advances in End-to-End (E2E) Spoken Language Understanding (SLU) have been primarily due to effective pretraining of speech representations. One such pretraining paradigm is the distillation of semantic knowledge from state-of-the-art text-based models like BERT to speech encoder neural networks. This work is a step towards doing the same in a much more efficient and fine-grained manner where we align speech embeddings and BERT embeddings on a token-by-token basis. We introduce a simple yet novel technique that uses a cross-modal attention mechanism to extract token-level contextual embeddings from a speech encoder such that these can be directly compared and aligned with BERT based contextual embeddings. This alignment is performed using a novel tokenwise contrastive loss. Fine-tuning such a pretrained model to perform intent recognition using speech directly yields state-of-the-art performance on two widely used SLU datasets. Our model improves further when fine-tuned with additional regularization using SpecAugment especially when speech is noisy, giving an absolute improvement as high as 8% over previous results.

Related papers

• CosyVoice: A Scalable Multilingual Zero-shot Text-to-speech Synthesizer based on Supervised Semantic Tokens [49.569695524535454]
  We propose to represent speech with supervised semantic tokens, which are derived from a multilingual speech recognition model by inserting vector quantization into the encoder. Based on the tokens, we further propose a scalable zero-shot TTS synthesizer, CosyVoice, which consists of an LLM for text-to-token generation and a conditional flow matching model for token-to-speech synthesis.
  arXiv  Detail & Related papers  (2024-07-07T15:16:19Z)
• BLSP-KD: Bootstrapping Language-Speech Pre-training via Knowledge Distillation [18.329192763760034]
  We introduce BLSP-KD, a novel approach for Bootstrapping Language-Speech Pretraining via Knowledge Distillation. It optimize speech-text alignment by minimizing the divergence between the LLM's next-token prediction distributions for speech and text inputs. It also employs a continuous-integrate-andfire strategy to segment speech into tokens that correspond one-to-one with text tokens, enabling fine-grained alignment.
  arXiv  Detail & Related papers  (2024-05-29T12:32:08Z)
• token2vec: A Joint Self-Supervised Pre-training Framework Using Unpaired Speech and Text [65.04385919645395]
  token2vec is a novel joint pre-training framework for unpaired speech and text based on discrete representations of speech. Experiments show that token2vec is significantly superior to various speech-only pre-training baselines, with up to 17.7% relative WER reduction.
  arXiv  Detail & Related papers  (2022-10-30T06:38:19Z)
• Supervision-Guided Codebooks for Masked Prediction in Speech Pre-training [102.14558233502514]
  Masked prediction pre-training has seen remarkable progress in self-supervised learning (SSL) for speech recognition. We propose two supervision-guided codebook generation approaches to improve automatic speech recognition (ASR) performance.
  arXiv  Detail & Related papers  (2022-06-21T06:08:30Z)
• Wav2Seq: Pre-training Speech-to-Text Encoder-Decoder Models Using Pseudo Languages [58.43299730989809]
  We introduce Wav2Seq, the first self-supervised approach to pre-train both parts of encoder-decoder models for speech data. We induce a pseudo language as a compact discrete representation, and formulate a self-supervised pseudo speech recognition task. This process stands on its own, or can be applied as low-cost second-stage pre-training.
  arXiv  Detail & Related papers  (2022-05-02T17:59:02Z)
• Speaker Embedding-aware Neural Diarization: a Novel Framework for Overlapped Speech Diarization in the Meeting Scenario [51.5031673695118]
  We reformulate overlapped speech diarization as a single-label prediction problem. We propose the speaker embedding-aware neural diarization (SEND) system.
  arXiv  Detail & Related papers  (2022-03-18T06:40:39Z)
• Improving Prosody for Unseen Texts in Speech Synthesis by Utilizing Linguistic Information and Noisy Data [20.132799566988826]
  We propose to combine a fine-tuned BERT-based front-end with a pre-trained FastSpeech2-based acoustic model to improve prosody modeling. Experimental results show that both the fine-tuned BERT model and the pre-trained FastSpeech 2 can improve prosody, especially for those structurally complex sentences.
  arXiv  Detail & Related papers  (2021-11-15T05:58:29Z)
• SLAM: A Unified Encoder for Speech and Language Modeling via Speech-Text Joint Pre-Training [33.02912456062474]
  We build a single encoder with the BERT objective on unlabeled text together with the w2v-BERT objective on unlabeled speech. We demonstrate that incorporating both speech and text data during pre-training can significantly improve downstream quality on CoVoST2 speech translation.
  arXiv  Detail & Related papers  (2021-10-20T00:59:36Z)
• Fast End-to-End Speech Recognition via a Non-Autoregressive Model and Cross-Modal Knowledge Transferring from BERT [72.93855288283059]
  We propose a non-autoregressive speech recognition model called LASO (Listen Attentively, and Spell Once) The model consists of an encoder, a decoder, and a position dependent summarizer (PDS)
  arXiv  Detail & Related papers  (2021-02-15T15:18:59Z)
• Two-stage Textual Knowledge Distillation for End-to-End Spoken Language Understanding [18.275646344620387]
  This work proposes a two-stage textual knowledge distillation method that matches utterance-level representations and predicted logits of two modalities during pre-training and fine-tuning. We push the state-of-the-art on the Fluent Speech Commands, achieving 99.7% test accuracy in the full dataset setting and 99.5% in the 10% subset setting.
  arXiv  Detail & Related papers  (2020-10-25T12:36:05Z)
• An Effective Contextual Language Modeling Framework for Speech Summarization with Augmented Features [13.97006782398121]
  Bidirectional Representations from Transformers (BERT) model was proposed and has achieved record-breaking success on many natural language processing tasks. We explore the incorporation of confidence scores into sentence representations to see if such an attempt could help alleviate the negative effects caused by imperfect automatic speech recognition. We validate the effectiveness of our proposed method on a benchmark dataset.
  arXiv  Detail & Related papers  (2020-06-01T18:27:48Z)

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.