Related papers: Data Augmentation Methods for End-to-end Speech Re…

Speech translation (ST) systems translate speech in one language to text in another language. End-to-end ST systems (e2e-ST) have gained popularity over cascade systems because of their enhanced performance due to reduced latency and…

End-to-end automatic speech recognition (E2E-ASR) has the potential to improve performance, but a specific issue that needs to be addressed is the difficulty it has in handling enharmonic words: named entities (NEs) with the same…

For automatic speech translation (AST), end-to-end approaches are outperformed by cascaded models that transcribe with automatic speech recognition (ASR), then translate with machine translation (MT). A major cause of the performance gap is…

Disordered speech recognition is a highly challenging task. The underlying neuro-motor conditions of people with speech disorders, often compounded with co-occurring physical disabilities, lead to the difficulty in collecting large…

Despite recent progress in automatic speech recognition (ASR), elderly ASR (EASR) remains challenging due to limited training data and the distinct acoustic and linguistic characteristics of elderly speech. In this work, we address data…

Data augmentation (DA) is ubiquitously used in training of Automatic Speech Recognition (ASR) models. DA offers increased data variability, robustness and generalization against different acoustic distortions. Recently, personalization of…

Confidence estimation, in which we estimate the reliability of each recognized token (e.g., word, sub-word, and character) in automatic speech recognition (ASR) hypotheses and detect incorrectly recognized tokens, is an important function…

This paper presents our system for the MISP-Meeting Challenge Track 2. The primary difficulty lies in the dataset, which contains strong background noise, reverberation, overlapping speech, and diverse meeting topics. To address these…

Speech recognition applications cover a range of different audio and text distributions, with different speaking styles, background noise, transcription punctuation and character casing. However, many speech recognition systems require…

Despite recent improvements in End-to-End Automatic Speech Recognition (E2E ASR) systems, the performance can degrade due to vocal characteristic mismatches between training and testing data, particularly with limited target speaker…

Many neural text-to-speech architectures can synthesize nearly natural speech from text inputs. These architectures must be trained with tens of hours of annotated and high-quality speech data. Compiling such large databases for every new…

In this paper, we propose an incremental learning method for end-to-end Automatic Speech Recognition (ASR) which enables an ASR system to perform well on new tasks while maintaining the performance on its originally learned ones. To…

Recently, the end-to-end training approach for multi-channel ASR has shown its effectiveness, which usually consists of a beamforming front-end and a recognition back-end. However, the end-to-end training becomes more difficult due to the…

Attention-based sequence-to-sequence models for speech recognition jointly train an acoustic model, language model (LM), and alignment mechanism using a single neural network and require only parallel audio-text pairs. Thus, the language…

Speech enhancement (SE) systems are typically evaluated using a variety of instrumental metrics. The use of automatic speech recognition (ASR) systems to evaluate SE performance is common in literature, usually in terms of word error rate…

While end-to-end ASR systems have proven competitive with the conventional hybrid approach, they are prone to accuracy degradation when it comes to noisy and low-resource conditions. In this paper, we argue that, even in such difficult…

Speech recognizers trained on close-talking speech do not generalize to distant speech and the word error rate degradation can be as large as 40% absolute. Most studies focus on tackling distant speech recognition as a separate problem,…

Most of the current speech data augmentation methods operate on either the raw waveform or the amplitude spectrum of speech. In this paper, we propose a novel speech data augmentation method called PhasePerturbation that operates…

This paper explores the use of adversarial examples in training speech recognition systems to increase robustness of deep neural network acoustic models. During training, the fast gradient sign method is used to generate adversarial…

Deep learning technologies have significantly advanced the performance of target speaker extraction (TSE) tasks. To enhance the generalization and robustness of these algorithms when training data is insufficient, data augmentation is a…