Predictive Speech Recognition and End-of-Utterance Detection Towards Spoken Dialog Systems

• URL: http://arxiv.org/abs/2409.19990v1
• Date: Mon, 30 Sep 2024 06:29:58 GMT
• Title: Predictive Speech Recognition and End-of-Utterance Detection Towards Spoken Dialog Systems
• Authors: Oswald Zink, Yosuke Higuchi, Carlos Mullov, Alexander Waibel, Tetsunori Kobayashi,
• Abstract summary: We study a function that can predict the forthcoming words and estimate the time remaining until the end of an utterance. We develop a cross-attention-based algorithm that incorporates both acoustic and linguistic information. Results demonstrate the proposed model's ability to predict upcoming words and estimate future EOU events up to 300ms prior to the actual EOU.
• Score: 55.99999020778169
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Effective spoken dialog systems should facilitate natural interactions with quick and rhythmic timing, mirroring human communication patterns. To reduce response times, previous efforts have focused on minimizing the latency in automatic speech recognition (ASR) to optimize system efficiency. However, this approach requires waiting for ASR to complete processing until a speaker has finished speaking, which limits the time available for natural language processing (NLP) to formulate accurate responses. As humans, we continuously anticipate and prepare responses even while the other party is still speaking. This allows us to respond appropriately without missing the optimal time to speak. In this work, as a pioneering study toward a conversational system that simulates such human anticipatory behavior, we aim to realize a function that can predict the forthcoming words and estimate the time remaining until the end of an utterance (EOU), using the middle portion of an utterance. To achieve this, we propose a training strategy for an encoder-decoder-based ASR system, which involves masking future segments of an utterance and prompting the decoder to predict the words in the masked audio. Additionally, we develop a cross-attention-based algorithm that incorporates both acoustic and linguistic information to accurately detect the EOU. The experimental results demonstrate the proposed model's ability to predict upcoming words and estimate future EOU events up to 300ms prior to the actual EOU. Moreover, the proposed training strategy exhibits general improvements in ASR performance.

Related papers

• Yeah, Un, Oh: Continuous and Real-time Backchannel Prediction with Fine-tuning of Voice Activity Projection [24.71649541757314]
  Short backchannel utterances such as "yeah" and "oh" play a crucial role in facilitating smooth and engaging dialogue. This paper proposes a novel method for real-time, continuous backchannel prediction using a fine-tuned Voice Activity Projection model.
  arXiv  Detail & Related papers  (2024-10-21T11:57:56Z)
• Internalizing ASR with Implicit Chain of Thought for Efficient Speech-to-Speech Conversational LLM [3.6950912517562435]
  We propose a method that implicitly internalizes ASR chain of thought into a speech LLM, enhancing its native speech understanding capabilities. Our approach reduces latency and improves the model's native understanding of speech, paving the way for more efficient and natural real-time audio interactions.
  arXiv  Detail & Related papers  (2024-09-25T20:59:12Z)
• Towards Unsupervised Speech Recognition Without Pronunciation Models [57.222729245842054]
  Most languages lack sufficient paired speech and text data to effectively train automatic speech recognition systems. We propose the removal of reliance on a phoneme lexicon to develop unsupervised ASR systems. We experimentally demonstrate that an unsupervised speech recognizer can emerge from joint speech-to-speech and text-to-text masked token-infilling.
  arXiv  Detail & Related papers  (2024-06-12T16:30:58Z)
• Personalized Predictive ASR for Latency Reduction in Voice Assistants [29.237198363254752]
  We introduce predictive automatic speech recognition, where we predict the full utterance from a partially observed utterance, and prefetch the response based on the predicted utterance. We evaluate our methods on an internal voice assistant dataset as well as the public SLURP dataset.
  arXiv  Detail & Related papers  (2023-05-23T08:05:43Z)
• Contextual-Utterance Training for Automatic Speech Recognition [65.4571135368178]
  We propose a contextual-utterance training technique which makes use of the previous and future contextual utterances. Also, we propose a dual-mode contextual-utterance training technique for streaming automatic speech recognition (ASR) systems. The proposed technique is able to reduce both the WER and the average last token emission latency by more than 6% and 40ms relative.
  arXiv  Detail & Related papers  (2022-10-27T08:10:44Z)
• 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)
• Direction-Aware Joint Adaptation of Neural Speech Enhancement and Recognition in Real Multiparty Conversational Environments [21.493664174262737]
  This paper describes noisy speech recognition for an augmented reality headset that helps verbal communication within real multiparty conversational environments. We propose a semi-supervised adaptation method that jointly updates the mask estimator and the ASR model at run-time using clean speech signals with ground-truth transcriptions and noisy speech signals with highly-confident estimated transcriptions.
  arXiv  Detail & Related papers  (2022-07-15T03:43:35Z)
• 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)
• Dynamic Acoustic Unit Augmentation With BPE-Dropout for Low-Resource End-to-End Speech Recognition [62.94773371761236]
  We consider building an effective end-to-end ASR system in low-resource setups with a high OOV rate. We propose a method of dynamic acoustic unit augmentation based on the BPE-dropout technique. Our monolingual Turkish Conformer established a competitive result with 22.2% character error rate (CER) and 38.9% word error rate (WER)
  arXiv  Detail & Related papers  (2021-03-12T10:10:13Z)
• Temporarily-Aware Context Modelling using Generative Adversarial Networks for Speech Activity Detection [43.662221486962274]
  We propose a novel joint learning framework for Speech Activity Detection (SAD) We utilise generative adversarial networks to automatically learn a loss function for joint prediction of the frame-wise speech/ non-speech classifications together with the next audio segment. We evaluate the proposed framework on multiple public benchmarks, including NIST OpenSAT' 17, AMI Meeting and HAVIC.
  arXiv  Detail & Related papers  (2020-04-02T02:33:13Z)

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.