View publication

In this paper, we investigate how the output representation of an end-to-end neural network affects multilingual automatic speech recognition (ASR). We study different representations including character-level, byte-level, byte pair encoding (BPE), and byte- level byte pair encoding (BBPE) representations, and analyze their strengths and weaknesses. We focus on developing a single end-to- end model to support utterance-based bilingual ASR, where speakers do not alternate between two languages in a single utterance but may change languages across utterances. We conduct our experiments on English and Mandarin dictation tasks, and we find that BBPE with penalty schemes can improve utterance-based bilingual ASR performance by 2% to 5% relative even with smaller number of outputs and fewer parameters. We conclude with analysis that indicates directions for further improving multilingual ASR.

Related readings and updates.

Audio-to-Intent Using Acoustic-Textual Subword Representations from End-to-End ASR

Accurate prediction of the user intent to interact with a voice assistant (VA) on a device (e.g. a smartphone) is critical for achieving naturalistic, engaging, and privacy-centric interactions with the VA. To this end, we present a novel approach to predict the user intention (whether the user is speaking to the device or not) directly from acoustic and textual information encoded at subword tokens which are obtained via an end-to-end (E2E) ASR…
See paper details

Integrating Categorical Features in End-To-End ASR

All-neural, end-to-end ASR systems gained rapid interest from the speech recognition community. Such systems convert speech input to text units using a single trainable neural network model. E2E models require large amounts of paired speech text data that is expensive to obtain. The amount of data available varies across different languages and dialects. It is critical to make use of all these data so that both low resource languages and high…
See paper details