Homophone Disambiguation Reveals Patterns of Context Mixing in Speech Transformers

• URL: http://arxiv.org/abs/2310.09925v1
• Date: Sun, 15 Oct 2023 19:24:13 GMT
• Title: Homophone Disambiguation Reveals Patterns of Context Mixing in Speech Transformers
• Authors: Hosein Mohebbi, Grzegorz Chrupa{\l}a, Willem Zuidema, Afra Alishahi
• Abstract summary: We investigate how measures of 'context-mixing' developed for text models can be adapted and applied to models of spoken language. We identify a linguistic phenomenon that is ideal for such a case study: homophony in French. Our findings reveal that representations in encoder-only models effectively incorporate these cues to identify the correct transcription, whereas encoders in encoder-decoder models mainly relegate the task of capturing contextual dependencies to decoder modules.
• Score: 12.44366147179659
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Transformers have become a key architecture in speech processing, but our understanding of how they build up representations of acoustic and linguistic structure is limited. In this study, we address this gap by investigating how measures of 'context-mixing' developed for text models can be adapted and applied to models of spoken language. We identify a linguistic phenomenon that is ideal for such a case study: homophony in French (e.g. livre vs livres), where a speech recognition model has to attend to syntactic cues such as determiners and pronouns in order to disambiguate spoken words with identical pronunciations and transcribe them while respecting grammatical agreement. We perform a series of controlled experiments and probing analyses on Transformer-based speech models. Our findings reveal that representations in encoder-only models effectively incorporate these cues to identify the correct transcription, whereas encoders in encoder-decoder models mainly relegate the task of capturing contextual dependencies to decoder modules.

Related papers

• SelfVC: Voice Conversion With Iterative Refinement using Self Transformations [42.97689861071184]
  SelfVC is a training strategy to improve a voice conversion model with self-synthesized examples. We develop techniques to derive prosodic information from the audio signal and SSL representations to train predictive submodules in the synthesis model. Our framework is trained without any text and achieves state-of-the-art results in zero-shot voice conversion on metrics evaluating naturalness, speaker similarity, and intelligibility of synthesized audio.
  arXiv  Detail & Related papers  (2023-10-14T19:51:17Z)
• Towards General-Purpose Text-Instruction-Guided Voice Conversion [84.78206348045428]
  This paper introduces a novel voice conversion model, guided by text instructions such as "articulate slowly with a deep tone" or "speak in a cheerful boyish voice" The proposed VC model is a neural language model which processes a sequence of discrete codes, resulting in the code sequence of converted speech.
  arXiv  Detail & Related papers  (2023-09-25T17:52:09Z)
• Enhance audio generation controllability through representation similarity regularization [23.320569279485472]
  We propose an innovative approach to enhance control over audio generation by emphasizing the alignment between audio and text representations during model training. Our proposed methods lead to improvements in objective metrics for both audio and music generation, as well as an enhancement in the human perception for audio generation.
  arXiv  Detail & Related papers  (2023-09-15T21:32:20Z)
• TokenSplit: Using Discrete Speech Representations for Direct, Refined, and Transcript-Conditioned Speech Separation and Recognition [51.565319173790314]
  TokenSplit is a sequence-to-sequence encoder-decoder model that uses the Transformer architecture. We show that our model achieves excellent performance in terms of separation, both with or without transcript conditioning. We also measure the automatic speech recognition (ASR) performance and provide audio samples of speech synthesis to demonstrate the additional utility of our model.
  arXiv  Detail & Related papers  (2023-08-21T01:52:01Z)
• How Generative Spoken Language Modeling Encodes Noisy Speech: Investigation from Phonetics to Syntactics [33.070158866023]
  generative spoken language modeling (GSLM) involves using learned symbols derived from data rather than phonemes for speech analysis and synthesis. This paper presents the findings of GSLM's encoding and decoding effectiveness at the spoken-language and speech levels.
  arXiv  Detail & Related papers  (2023-06-01T14:07:19Z)
• 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)
• Towards Language Modelling in the Speech Domain Using Sub-word Linguistic Units [56.52704348773307]
  We propose a novel LSTM-based generative speech LM based on linguistic units including syllables and phonemes. With a limited dataset, orders of magnitude smaller than that required by contemporary generative models, our model closely approximates babbling speech. We show the effect of training with auxiliary text LMs, multitask learning objectives, and auxiliary articulatory features.
  arXiv  Detail & Related papers  (2021-10-31T22:48:30Z)
• VQMIVC: Vector Quantization and Mutual Information-Based Unsupervised Speech Representation Disentanglement for One-shot Voice Conversion [54.29557210925752]
  One-shot voice conversion can be effectively achieved by speech representation disentanglement. We employ vector quantization (VQ) for content encoding and introduce mutual information (MI) as the correlation metric during training. Experimental results reflect the superiority of the proposed method in learning effective disentangled speech representations.
  arXiv  Detail & Related papers  (2021-06-18T13:50:38Z)
• Bridging the Modality Gap for Speech-to-Text Translation [57.47099674461832]
  End-to-end speech translation aims to translate speech in one language into text in another language via an end-to-end way. Most existing methods employ an encoder-decoder structure with a single encoder to learn acoustic representation and semantic information simultaneously. We propose a Speech-to-Text Adaptation for Speech Translation model which aims to improve the end-to-end model performance by bridging the modality gap between speech and text.
  arXiv  Detail & Related papers  (2020-10-28T12:33:04Z)
• Contextualized Spoken Word Representations from Convolutional Autoencoders [2.28438857884398]
  This paper proposes a Convolutional Autoencoder based neural architecture to model syntactically and semantically adequate contextualized representations of varying length spoken words. The proposed model was able to demonstrate its robustness when compared to the other two language-based models.
  arXiv  Detail & Related papers  (2020-07-06T16:48:11Z)

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.