[PDF][PDF] Time-synchronous one-pass beam search for parallel online and offline transducers with dynamic block training
End-to-end automatic speech recognition (ASR) has become an increasingly popular area
of research, with two main models being online and offline ASR. Online models aim to …
of research, with two main models being online and offline ASR. Online models aim to …
Contextualized Automatic Speech Recognition With Attention-Based Bias Phrase Boosted Beam Search
End-to-end (E2E) automatic speech recognition (ASR) methods exhibit remarkable
performance. However, since the performance of such methods is intrinsically linked to the …
performance. However, since the performance of such methods is intrinsically linked to the …
Contextualized End-to-end Automatic Speech Recognition with Intermediate Biasing Loss
Contextualized end-to-end automatic speech recognition has been an active research area,
with recent efforts focusing on the implicit learning of contextual phrases based on the final …
with recent efforts focusing on the implicit learning of contextual phrases based on the final …
4D ASR: Joint Beam Search Integrating CTC, Attention, Transducer, and Mask Predict Decoders
End-to-end automatic speech recognition (E2E-ASR) can be classified into several network
architectures, such as connectionist temporal classification (CTC), recurrent neural network …
architectures, such as connectionist temporal classification (CTC), recurrent neural network …
Listening to Multi-talker Conversations: Modular and End-to-end Perspectives
D Raj - arXiv preprint arXiv:2402.08932, 2024 - arxiv.org
Since the first speech recognition systems were built more than 30 years ago, improvement
in voice technology has enabled applications such as smart assistants and automated …
in voice technology has enabled applications such as smart assistants and automated …
Towards Effective and Efficient Non-autoregressive Decoding Using Block-based Attention Mask
This paper proposes a novel non-autoregressive (NAR) block-based Attention Mask
Decoder (AMD) that flexibly balances performance-efficiency trade-offs for Conformer ASR …
Decoder (AMD) that flexibly balances performance-efficiency trade-offs for Conformer ASR …
Joint Optimization of Streaming and Non-Streaming Automatic Speech Recognition with Multi-Decoder and Knowledge Distillation
End-to-end (E2E) automatic speech recognition (ASR) can operate in two modes: streaming
and non-streaming, each with its pros and cons. Streaming ASR processes the speech …
and non-streaming, each with its pros and cons. Streaming ASR processes the speech …
Online adaptation of fourier series-based acoustic transfer function model and its application to sound source localization and separation
In this paper, we propose an online adaptation method for Fourier series-based acoustic
transfer function (FS-ATF) models for robot audition systems using microphone array signal …
transfer function (FS-ATF) models for robot audition systems using microphone array signal …
Contextualized Automatic Speech Recognition with Dynamic Vocabulary
Deep biasing (DB) improves the performance of end-to-end automatic speech recognition
(E2E-ASR) for rare words or contextual phrases using a bias list. However, most existing …
(E2E-ASR) for rare words or contextual phrases using a bias list. However, most existing …
Improving Noise Robustness of Automatic Speech Recognition Based on a Parallel Adapter Model with Near-Identity Initialization
This paper proposes the parallel adapter model (PAM) to improve the noise-robustness of
automatic speech recognition (ASR) systems with a small amount of retraining. The …
automatic speech recognition (ASR) systems with a small amount of retraining. The …