Related papers: Learning Phone Recognition from Unpaired Audio and…
Speech systems developed for a particular choice of acoustic domain and sampling frequency do not translate easily to others. The usual practice is to learn domain adaptation and bandwidth extension models independently. Contrary to this,…
Millions of hearing impaired people around the world routinely use some variants of sign languages to communicate, thus the automatic translation of a sign language is meaningful and important. Currently, there are two sub-problems in Sign…
Multilingual training has been shown to improve acoustic modeling performance by sharing and transferring knowledge in modeling different languages. Knowledge sharing is usually achieved by using common lower-level layers for different…
Previous speech pre-training methods, such as wav2vec2.0 and HuBERT, pre-train a Transformer encoder to learn deep representations from audio data, with objectives predicting either elements from latent vector quantized space or…
Phone-level pronunciation scoring is a challenging task, with performance far from that of human annotators. Standard systems generate a score for each phone in a phrase using models trained for automatic speech recognition (ASR) with…
Labeled audio data is insufficient to build satisfying speech recognition systems for most of the languages in the world. There have been some zero-resource methods trying to perform phoneme or word-level speech recognition without labeled…
Speech enhancement has seen great improvement in recent years using end-to-end neural networks. However, most models are agnostic to the spoken phonetic content. Recently, several studies suggested phonetic-aware speech enhancement, mostly…
Most of the previous approaches to lyrics-to-audio alignment used a pre-developed automatic speech recognition (ASR) system that innately suffered from several difficulties to adapt the speech model to individual singers. A significant…
We introduce Generative Spoken Language Modeling, the task of learning the acoustic and linguistic characteristics of a language from raw audio (no text, no labels), and a set of metrics to automatically evaluate the learned representations…
Many of the recent advances in speech separation are primarily aimed at synthetic mixtures of short audio utterances with high degrees of overlap. Most of these approaches need an additional stitching step to stitch the separated speech…
Dysarthric speech recognition (DSR) presents a formidable challenge due to inherent inter-speaker variability, leading to severe performance degradation when applying DSR models to new dysarthric speakers. Traditional speaker adaptation…
Speech separation refers to extracting each individual speech source in a given mixed signal. Recent advancements in speech separation and ongoing research in this area, have made these approaches as promising techniques for pre-processing…
Human can recognize speech, as well as the peculiar accent of the speech simultaneously. However, present state-of-the-art ASR system can rarely do that. In this paper, we propose a multilingual approach to recognizing English speech, and…
In a pipeline speech translation system, automatic speech recognition (ASR) system will transmit errors in recognition to the downstream machine translation (MT) system. A standard machine translation system is usually trained on parallel…
Transformer-based architectures have been the subject of research aimed at understanding their overparameterization and the non-uniform importance of their layers. Applying these approaches to Automatic Speech Recognition, we demonstrate…
Neural speech separation has made remarkable progress and its integration with automatic speech recognition (ASR) is an important direction towards realizing multi-speaker ASR. This work provides an insightful investigation of speech…
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…
Self-supervised learning (SSL) methods have proven to be very successful in automatic speech recognition (ASR). These great improvements have been reported mostly based on highly curated datasets such as LibriSpeech for non-streaming…
In this work, we showcase a cost-effective method for generating training data for speech processing tasks. First, we transcribe unlabeled speech using a state-of-the-art Automatic Speech Recognition (ASR) model. Next, we align generated…
Producing a large amount of annotated speech data for training ASR systems remains difficult for more than 95% of languages all over the world which are low-resourced. However, we note human babies start to learn the language by the sounds…