Related papers: ChannelAugment: Improving generalization of multi-…
Practitioners often need to build ASR systems for new use cases in a short amount of time, given limited in-domain data. While recently developed end-to-end methods largely simplify the modeling pipelines, they still suffer from the data…
Data synthesis and augmentation are essential for Sound Event Detection (SED) due to the scarcity of temporally labeled data. While augmentation methods like SpecAugment and Mix-up can enhance model performance, they remain constrained by…
When a sufficiently large far-field training data is presented, jointly optimizing a multichannel frontend and an end-to-end (E2E) Automatic Speech Recognition (ASR) backend shows promising results. Recent literature has shown traditional…
This work investigates a simple data augmentation technique, SpecAugment, for end-to-end speech translation. SpecAugment is a low-cost implementation method applied directly to the audio input features and it consists of masking blocks of…
The performance of automatic speech recognition (ASR) systems has advanced substantially in recent years, particularly for languages for which a large amount of transcribed speech is available. Unfortunately, for low-resource languages,…
Using neural network based acoustic frontends for improving robustness of streaming automatic speech recognition (ASR) systems is challenging because of the causality constraints and the resulting distortion that the frontend processing…
Joint optimization of multi-channel front-end and automatic speech recognition (ASR) has attracted much interest. While promising results have been reported for various tasks, past studies on its meeting transcription application were…
Data augmentation (DA) is widely employed to improve the generalization performance of deep models. However, most existing DA methods employ augmentation operations with fixed or random magnitudes throughout the training process. While this…
Consistency regularization has recently been applied to semi-supervised sequence-to-sequence (S2S) automatic speech recognition (ASR). This principle encourages an ASR model to output similar predictions for the same input speech with…
We previously proposed contextual spelling correction (CSC) to correct the output of end-to-end (E2E) automatic speech recognition (ASR) models with contextual information such as name, place, etc. Although CSC has achieved reasonable…
Automatic speech recognition (ASR) research has achieved impressive performance in recent years and has significant potential for enabling access for people with dysarthria (PwD) in augmentative and alternative communication (AAC) and home…
Usually, hearing impaired people use hearing aids which are implemented with speech enhancement algorithms. Estimation of speech and estimation of nose are the components in single channel speech enhancement system. The main objective of…
Speech-based virtual assistants, such as Amazon Alexa, Google assistant, and Apple Siri, typically convert users' audio signals to text data through automatic speech recognition (ASR) and feed the text to downstream dialog models for…
One-shot magnitude pruning can cause severe accuracy collapse in the high-sparsity regime, even when the pruning mask preserves the largest weights. We argue that this failure reflects a granularity mismatch in post-pruning repair. Under…
Data augmentation is one of the most effective ways to make end-to-end automatic speech recognition (ASR) perform close to the conventional hybrid approach, especially when dealing with low-resource tasks. Using recent advances in speech…
Deep learning has become a de facto method of choice for speech enhancement tasks with significant improvements in speech quality. However, real-time processing with reduced size and computations for low-power edge devices drastically…
With the surge of online meetings, it has become more critical than ever to provide high-quality speech audio and live captioning under various noise conditions. However, most monaural speech enhancement (SE) models introduce processing…
In this paper, we present SpecAugment++, a novel data augmentation method for deep neural networks based acoustic scene classification (ASC). Different from other popular data augmentation methods such as SpecAugment and mixup that only…
Data augmentation (DA) is a crucial technique for enhancing the sample efficiency of visual reinforcement learning (RL) algorithms. Notably, employing simple observation transformations alone can yield outstanding performance without extra…
Automatic Speech Recognition (ASR) systems suffer considerably when source speech is corrupted with noise or room impulse responses (RIR). Typically, speech enhancement is applied in both mismatched and matched scenario training and…