相关论文: Minimising Biasing Word Errors for Contextual ASR …

Continual learning for automatic speech recognition (ASR) systems poses a challenge, especially with the need to avoid catastrophic forgetting while maintaining performance on previously learned tasks. This paper introduces a novel approach…

Vision-language models (VLMs) pre-trained on web-scale data exhibit promising zero-shot generalization but often suffer from semantic misalignment due to domain gaps between pre-training and downstream tasks. Existing approaches primarily…

We present automatic speech recognition (ASR) systems for Tamil and Kannada based on subword modeling to effectively handle unlimited vocabulary due to the highly agglutinative nature of the languages. We explore byte pair encoding (BPE),…

Large language model (LLM)-based automatic speech recognition (ASR) has recently achieved strong performance across diverse tasks, yet contextual biasing for named entities and hotwords under large vocabularies remains challenging. In this…

Sequence-to-sequence attention-based models integrate an acoustic, pronunciation and language model into a single neural network, which make them very suitable for multilingual automatic speech recognition (ASR). In this paper, we are…

Supervised ASR models have reached unprecedented levels of accuracy, thanks in part to ever-increasing amounts of labelled training data. However, in many applications and locales, only moderate amounts of data are available, which has led…

Comparing spoken segments is a central operation to speech processing. Traditional approaches in this area have favored frame-level dynamic programming algorithms, such as dynamic time warping, because they require no supervision, but they…

The development of resource-constrained approaches to automatic speech recognition (ASR) is of great interest due to its broad applicability to many low-resource languages for which there is scant usable data. Existing approaches to many…

This paper presents a Pronunciation-Aware Contextualized (PAC) framework to address two key challenges in Large Language Model (LLM)-based Automatic Speech Recognition (ASR) systems: effective pronunciation modeling and robust homophone…

In this work, we describe a novel method of training an embedding-matching word-level connectionist temporal classification (CTC) automatic speech recognizer (ASR) such that it directly produces word start times and durations, required by…

Accented automatic speech recognition (ASR) often degrades due to the limited availability of accented training data. Prior work has explored accent modeling in low-resource settings, but existing approaches typically require minutes to…

Single-word Automatic Speech Recognition (ASR) is a challenging task due to the lack of linguistic context and sensitivity to noise, pronunciation variation, and channel artifacts, especially in low-resource, communication-critical domains…

Discrete audio tokens derived from self-supervised learning models have gained widespread usage in speech generation. However, current practice of directly utilizing audio tokens poses challenges for sequence modeling due to the length of…

The quality of automatic speech recognition (ASR) is critical to Dialogue Systems as ASR errors propagate to and directly impact downstream tasks such as language understanding (LU). In this paper, we propose multi-task neural approaches to…

The performance of automatic speech recognition (ASR) has improved tremendously due to the application of deep neural networks (DNNs). Despite this progress, building a new ASR system remains a challenging task, requiring various resources,…

This paper studies contextual biasing with Large Language Models (LLMs), where during second-pass rescoring additional contextual information is provided to a LLM to boost Automatic Speech Recognition (ASR) performance. We propose to…

Recent dialogue systems rely on turn-based spoken interactions, requiring accurate Automatic Speech Recognition (ASR). Errors in ASR can significantly impact downstream dialogue tasks. To address this, using dialogue context from user and…

This paper proposes an adaptation method for end-to-end speech recognition. In this method, multiple automatic speech recognition (ASR) 1-best hypotheses are integrated in the computation of the connectionist temporal classification (CTC)…

Automatic speech recognition (ASR) systems often make unrecoverable errors due to subsystem pruning (acoustic, language and pronunciation models); for example pruning words due to acoustics using short-term context, prior to rescoring with…

At the present time, computers are employed to solve complex tasks and problems ranging from simple calculations to intensive digital image processing and intricate algorithmic optimization problems to computationally-demanding weather…