We present two end-to-end models: Audio-to-Byte (A2B) and Byte-to-Audio (B2A), for
multilingual speech recognition and synthesis. Prior work has predominantly used …

There is an implicit assumption that traditional hybrid approaches for automatic speech
recognition (ASR) cannot directly model graphemes and need to rely on phonetic lexicons to …

End-to-end automatic speech recognition (ASR) models with a single neural network have
recently demonstrated state-of-the-art results compared to conventional hybrid speech …

The performance of automatic speech recognition can often be significantly improved by
combining multiple systems together. Though beneficial, ensemble methods can be …

Building speech recognizers in multiple languages typically involves replicating a
monolingual training recipe for each language, or utilizing a multi-task learning approach …

Modeling voices for multiple speakers and multiple languages with one speech synthesis
system has been a challenge for a long time, especially in low-resource cases. This paper …

Foundation ASR models often support many languages, eg 100 languages in Whisper.
However, there has been limited work on integrating an additional, typically low-resource …

Deep learning approaches yield state-of-the-art performance in a range of tasks, including
automatic speech recognition. However, the highly distributed representation in a deep …

The IARPA BABEL program has stimulated worldwide research in keyword search
technology for low resource languages, and the NIST OpenKWS evaluations are the de …

Towards developing high-performing ASR for low-resource languages, approaches to
address the lack of resources are to make use of data from multiple languages, and to …