Related papers: Extending Recurrent Neural Aligner for Streaming E…
Multilingual end-to-end automatic speech recognition models are attractive due to its simplicity in training and deployment. Recent work on large-scale training of such models has shown promising results compared to monolingual models.…
Adapting End-to-End ASR models to out-of-domain datasets with text data is challenging. Factorized neural Transducer (FNT) aims to address this issue by introducing a separate vocabulary decoder to predict the vocabulary. Nonetheless, this…
Non-autoregressive (NAR) models simultaneously generate multiple outputs in a sequence, which significantly reduces the inference speed at the cost of accuracy drop compared to autoregressive baselines. Showing great potential for real-time…
End-to-end approaches for automatic speech recognition (ASR) benefit from directly modeling the probability of the word sequence given the input audio stream in a single neural network. However, compared to conventional ASR systems, these…
Deep neural network-based systems have significantly improved the performance of speaker diarization tasks. However, end-to-end neural diarization (EEND) systems often struggle to generalize to scenarios with an unseen number of speakers,…
On-device end-to-end (E2E) models have shown improvements over a conventional model on English Voice Search tasks in both quality and latency. E2E models have also shown promising results for multilingual automatic speech recognition (ASR).…
We live in a world where 60% of the population can speak two or more languages fluently. Members of these communities constantly switch between languages when having a conversation. As automatic speech recognition (ASR) systems are being…
The front-end module in multi-channel automatic speech recognition (ASR) systems mainly use microphone array techniques to produce enhanced signals in noisy conditions with reverberation and echos. Recently, neural network (NN) based…
Improving the performance of end-to-end ASR models on long utterances ranging from minutes to hours in length is an ongoing challenge in speech recognition. A common solution is to segment the audio in advance using a separate voice…
Mainstream Automatic Speech Recognition (ASR) systems excel at transcribing lexical content, but largely fail to recognize nonverbal vocalizations (NVs) embedded in speech, such as sighs, laughs, and coughs. This capability is important for…
Using end-to-end models for speech translation (ST) has increasingly been the focus of the ST community. These models condense the previously cascaded systems by directly converting sound waves into translated text. However, cascaded models…
Multi-channel inputs offer several advantages over single-channel, to improve the robustness of on-device speech recognition systems. Recent work on multi-channel transformer, has proposed a way to incorporate such inputs into end-to-end…
Recently, online end-to-end ASR has gained increasing attention. However, the performance of online systems still lags far behind that of offline systems, with a large gap in quality of recognition. For specific scenarios, we can trade-off…
End-to-end (E2E) automatic speech recognition (ASR) models, by now, have shown competitive performance on several benchmarks. These models are structured to either operate in streaming or non-streaming mode. This work presents cascaded…
Non-autoregressive automatic speech recognition (ASR) has become a mainstream of ASR modeling because of its fast decoding speed and satisfactory result. To further boost the performance, relaxing the conditional independence assumption and…
In this work, we introduce a simple yet efficient post-processing model for automatic speech recognition (ASR). Our model has Transformer-based encoder-decoder architecture which "translates" ASR model output into grammatically and…
With the recent advances in technology, automatic speech recognition (ASR) has been widely used in real-world applications. The efficiency of converting large amounts of speech into text accurately with limited resources has become more…
In this paper, we propose an end-to-end Mandarin tone classification method from continuous speech utterances utilizing both the spectrogram and the short-term context information as the input. Both spectrograms and context segment features…
Non-autoregressive (NAR) modeling has gained significant interest in speech processing since these models achieve dramatically lower inference time than autoregressive (AR) models while also achieving good transcription accuracy. Since NAR…
This paper presents our recent effort on end-to-end speaker-attributed automatic speech recognition, which jointly performs speaker counting, speech recognition and speaker identification for monaural multi-talker audio. Firstly, we…