Related papers: 4-bit Conformer with Native Quantization Aware Tra…
We present a Conformer-based end-to-end neural diarization (EEND) model that uses both acoustic input and features derived from an automatic speech recognition (ASR) model. Two categories of features are explored: features derived directly…
Neural audio coding has emerged as a vivid research direction by promising good audio quality at very low bitrates unachievable by classical coding techniques. Here, end-to-end trainable autoencoder-like models represent the state of the…
Self-supervised learning has been proved to benefit a wide range of speech processing tasks, such as speech recognition/translation, speaker verification and diarization, etc. However, most of current approaches are computationally…
State-of-the-art neural language models represented by Transformers are becoming increasingly complex and expensive for practical applications. Low-bit deep neural network quantization techniques provides a powerful solution to dramatically…
We consider the problem of recognizing speech utterances spoken to a device which is generating a known sound waveform; for example, recognizing queries issued to a digital assistant which is generating responses to previous user inputs.…
As speech processing systems in mobile and edge devices become more commonplace, the demand for unintrusive speech quality monitoring increases. Deep learning methods provide high-quality estimates of objective and subjective speech quality…
The performances of automatic speech recognition (ASR) systems are usually evaluated by the metric word error rate (WER) when the manually transcribed data are provided, which are, however, expensively available in the real scenario. In…
Self-supervised speech recognition models require considerable labeled training data for learning high-fidelity representations for Automatic Speech Recognition (ASR) which is computationally demanding and time-consuming. We consider the…
The recent emergence of joint CTC-Attention model shows significant improvement in automatic speech recognition (ASR). The improvement largely lies in the modeling of linguistic information by decoder. The decoder joint-optimized with an…
Acoustic Echo Cancellation (AEC) is essential for accurate recognition of queries spoken to a smart speaker that is playing out audio. Previous work has shown that a neural AEC model operating on log-mel spectral features (denoted "logmel"…
Automatic speech recognition (ASR) systems are primarily evaluated on transcription accuracy. However, in some use cases such as subtitling, verbatim transcription would reduce output readability given limited screen size and reading time.…
Deploying Automatic Speech Recognition (ASR) models on memory-constrained edge devices requires aggressive low-bit weight quantization. Layer-wise post-training quantization is practical and effective, but it suffers from cross-layer error…
Building competitive automatic speech recognition (ASR) models usually requires large-scale au- dio supervision, which makes reproduction and specialization expensive. We study Ark-ASR, a 0.6B- parameter audio-conditioned language model…
Supervised training of speech recognition models requires access to transcribed audio data, which often is not possible due to confidentiality issues. Our approach to this problem is to generate synthetic audio from a text-only corpus using…
Automatic speech recognition (ASR) is a key area in computational linguistics, focusing on developing technologies that enable computers to convert spoken language into text. This field combines linguistics and machine learning. ASR models,…
In this paper, we analyzed how audio-visual speech enhancement can help to perform the ASR task in a cocktail party scenario. Therefore we considered two simple end-to-end LSTM-based models that perform single-channel audio-visual speech…
Scores from traditional confidence classifiers (CCs) in automatic speech recognition (ASR) systems lack universal interpretation and vary with updates to the underlying confidence or acoustic models (AMs). In this work, we build…
This paper proposes an efficient attempt to noisy speech emotion recognition (NSER). Conventional NSER approaches have proven effective in mitigating the impact of artificial noise sources, such as white Gaussian noise, but are limited to…
Quantization-aware training (QAT) is widely adopted to quantize language models by training full-precision weights using gradients from the quantized model. The main bottleneck is its slow convergence and early performance plateau,…
We present a comprehensive study of deep bidirectional long short-term memory (LSTM) recurrent neural network (RNN) based acoustic models for automatic speech recognition (ASR). We study the effect of size and depth and train models of up…