Related papers: Exploring End-to-End Techniques for Low-Resource S…
We propose a single neural network architecture for two tasks: on-line keyword spotting and voice activity detection. We develop novel inference algorithms for an end-to-end Recurrent Neural Network trained with the Connectionist Temporal…
Producing a large amount of annotated speech data for training ASR systems remains difficult for more than 95% of languages all over the world which are low-resourced. However, we note human babies start to learn the language by the sounds…
We present software that, in only a few hours, transcribes forty hours of recorded speech in a surprise language, using only a few tens of megabytes of noisy text in that language, and a zero-resource grapheme to phoneme (G2P) table. A…
The attention-based Transformer model has achieved promising results for speech recognition (SR) in the offline mode. However, in the streaming mode, the Transformer model usually incurs significant latency to maintain its recognition…
Despite rapid progress in the recent past, current speech recognition systems still require labeled training data which limits this technology to a small fraction of the languages spoken around the globe. This paper describes wav2vec-U,…
Attention-based models have been gaining popularity recently for their strong performance demonstrated in fields such as machine translation and automatic speech recognition. One major challenge of attention-based models is the need of…
Speech recognisers usually perform optimally only in a specific environment and need to be adapted to work well in another. For adaptation to a new speaker, there is often too little data for fine-tuning to be robust, and that data is…
We study training a single end-to-end (E2E) automatic speech recognition (ASR) model for three languages used in Kazakhstan: Kazakh, Russian, and English. We first describe the development of multilingual E2E ASR based on Transformer…
While the Turkish language is listed among low-resource languages, literature on Turkish automatic speech recognition (ASR) is relatively old. In this report, we present our findings on Turkish ASR with speech representation learning using…
In the recent literature, "end-to-end" speech systems often refer to letter-based acoustic models trained in a sequence-to-sequence manner, either via a recurrent model or via a structured output learning approach (such as CTC). In contrast…
We study pseudo-labeling for the semi-supervised training of ResNet, Time-Depth Separable ConvNets, and Transformers for speech recognition, with either CTC or Seq2Seq loss functions. We perform experiments on the standard LibriSpeech…
End-to-end models with auto-regressive decoders have shown impressive results for automatic speech recognition (ASR). These models formulate the sequence-level probability as a product of the conditional probabilities of all individual…
This work presents an approach for recognizing isolated sign language gestures using skeleton-based pose data extracted from video sequences. A Graph-GRU temporal network is proposed to model both spatial and temporal dependencies between…
Recognizing emotions from speech using machine learning has become an active research area due to its importance in building human-centered applications. However, while many studies have been conducted in English, German, and other European…
Code-switching (CS), defined as the mixing of languages in conversations, has become a worldwide phenomenon. The prevalence of CS has been recently met with a growing demand and interest to build CS ASR systems. In this paper, we present…
End-to-end models have achieved impressive results on the task of automatic speech recognition (ASR). For low-resource ASR tasks, however, labeled data can hardly satisfy the demand of end-to-end models. Self-supervised acoustic…
This study describes our system for Task 1 Single-speaker Visual Speech Recognition (VSR) fixed track in the Chinese Continuous Visual Speech Recognition Challenge (CNVSRC) 2023. Specifically, we use intermediate connectionist temporal…
Traditional visual speech recognition systems consist of two stages, feature extraction and classification. Recently, several deep learning approaches have been presented which automatically extract features from the mouth images and aim to…
This paper describes a novel text-to-speech (TTS) technique based on deep convolutional neural networks (CNN), without use of any recurrent units. Recurrent neural networks (RNN) have become a standard technique to model sequential data…
State-of-the-art neural network language models (NNLMs) represented by long short term memory recurrent neural networks (LSTM-RNNs) and Transformers are becoming highly complex. They are prone to overfitting and poor generalization when…