Related papers: Toward Cross-Domain Speech Recognition with End-to…
Current state-of-the-art automatic speech recognition systems are trained to work in specific `domains', defined based on factors like application, sampling rate and codec. When such recognizers are used in conditions that do not match the…
A key desiderata for inclusive and accessible speech recognition technology is ensuring its robust performance to children's speech. Notably, this includes the rapidly advancing neural network based end-to-end speech recognition systems.…
End-to-end deep learning language or dialect identification systems operate on the spectrogram or other acoustic feature and directly generate identification scores for each class. An important issue for end-to-end systems is to have some…
The field of speech recognition is in the midst of a paradigm shift: end-to-end neural networks are challenging the dominance of hidden Markov models as a core technology. Using an attention mechanism in a recurrent encoder-decoder…
Conversational context information, higher-level knowledge that spans across sentences, can help to recognize a long conversation. However, existing speech recognition models are typically built at a sentence level, and thus it may not…
We present a hybrid framework that leverages the trade-off between temporal and frequency precision in audio representations to improve the performance of speech enhancement task. We first show that conventional approaches using specific…
Recent advances in deep learning and automatic speech recognition (ASR) have enabled the end-to-end (E2E) ASR system and boosted the accuracy to a new level. The E2E systems implicitly model all conventional ASR components, such as the…
In many automatic speech recognition (ASR) tasks, an ideal model has to be applicable over multiple domains. In this paper, we propose to teach an all-rounder with experts in different domains. Concretely, we build a multi-domain acoustic…
While recent automatic speech recognition systems achieve remarkable performance when large amounts of adequate, high quality annotated speech data is used for training, the same systems often only achieve an unsatisfactory result for tasks…
How to leverage dynamic contextual information in end-to-end speech recognition has remained an active research area. Previous solutions to this problem were either designed for specialized use cases that did not generalize well to…
End-to-end models for robust automatic speech recognition (ASR) have not been sufficiently well-explored in prior work. With end-to-end models, one could choose to preprocess the input speech using speech enhancement techniques and train…
Continual learning for end-to-end automatic speech recognition has to contend with a number of difficulties. Fine-tuning strategies tend to lose performance on data already seen, a process known as catastrophic forgetting. On the other…
Existing speech recognition systems are typically built at the sentence level, although it is known that dialog context, e.g. higher-level knowledge that spans across sentences or speakers, can help the processing of long conversations. The…
Acoustics-to-word models are end-to-end speech recognizers that use words as targets without relying on pronunciation dictionaries or graphemes. These models are notoriously difficult to train due to the lack of linguistic knowledge. It is…
Neural models have become ubiquitous in automatic speech recognition systems. While neural networks are typically used as acoustic models in more complex systems, recent studies have explored end-to-end speech recognition systems based on…
End-to-end acoustic-to-word speech recognition models have recently gained popularity because they are easy to train, scale well to large amounts of training data, and do not require a lexicon. In addition, word models may also be easier to…
Recently, end-to-end models have become a popular approach as an alternative to traditional hybrid models in automatic speech recognition (ASR). The multi-speaker speech separation and recognition task is a central task in cocktail party…
This paper explores the integration of model-based and data-driven approaches within the realm of neural speech and audio coding systems. It highlights the challenges posed by the subjective evaluation processes of speech and audio codecs…
With the advent of modern AI architectures, a shift has happened towards end-to-end architectures. This pivot has led to neural architectures being trained without domain-specific biases/knowledge, optimized according to the task. We in…
Previous work has shown that it is possible to improve speech recognition by learning acoustic features from paired acoustic-articulatory data, for example by using canonical correlation analysis (CCA) or its deep extensions. One limitation…