Related papers: Alignment Restricted Streaming Recurrent Neural Ne…

Modern systems for automatic speech recognition, including the RNN-Transducer and Attention-based Encoder-Decoder (AED), are designed so that the encoder is not required to alter the time-position of information from the audio sequence into…

We introduce Speech ReaLLM, a new ASR architecture that marries "decoder-only" ASR with the RNN-T to make multimodal LLM architectures capable of real-time streaming. This is the first "decoder-only" ASR architecture designed to handle…

Automatic speech recognition (ASR) and speech translation (ST) can both use neural transducers as the model structure. It is thus possible to use a single transducer model to perform both tasks. In real-world applications, such joint ASR…

This paper describes a variational auto-encoder based non-autoregressive text-to-speech (VAENAR-TTS) model. The autoregressive TTS (AR-TTS) models based on the sequence-to-sequence architecture can generate high-quality speech, but their…

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…

End-to-end (E2E) models have shown to outperform state-of-the-art conventional models for streaming speech recognition [1] across many dimensions, including quality (as measured by word error rate (WER)) and endpointer latency [2]. However,…

Convolutional Neural Networks (CNNs) are effective models for reducing spectral variations and modeling spectral correlations in acoustic features for automatic speech recognition (ASR). Hybrid speech recognition systems incorporating CNNs…

Recently sequence-to-sequence models have started to achieve state-of-the-art performance on standard speech recognition tasks when processing audio data in batch mode, i.e., the complete audio data is available when starting processing.…

The speech chain mechanism integrates automatic speech recognition (ASR) and text-to-speech synthesis (TTS) modules into a single cycle during training. In our previous work, we applied a speech chain mechanism as a semi-supervised…

Recurrent neural networks (RNNs) are commonly trained with the truncated backpropagation-through-time (TBPTT) algorithm. For the purposes of computational tractability, the TBPTT algorithm truncates the chain rule and calculates the…

Recent advances in large language models (LLMs) have attracted significant interest in extending their capabilities to multimodal scenarios, particularly for speech-to-speech conversational systems. However, existing multimodal models…

In this work, we propose a new automatic speech recognition (ASR) system based on feature learning and an end-to-end training procedure for air traffic control (ATC) systems. The proposed model integrates the feature learning block,…

Countless learning tasks require dealing with sequential data. Image captioning, speech synthesis, and music generation all require that a model produce outputs that are sequences. In other domains, such as time series prediction, video…

The growing need for instant spoken language transcription and translation is driven by increased global communication and cross-lingual interactions. This has made offering translations in multiple languages essential for user…

Recently, several types of end-to-end speech recognition methods named transformer-transducer were introduced. According to those kinds of methods, transcription networks are generally modeled by transformer-based neural networks, while…

Having a sequence-to-sequence model which can operate in an online fashion is important for streaming applications such as Voice Search. Neural transducer is a streaming sequence-to-sequence model, but has shown a significant degradation in…

Recurrent neural networks (RNNs), such as long short-term memory networks (LSTMs), serve as a fundamental building block for many sequence learning tasks, including machine translation, language modeling, and question answering. In this…

In real-time speech recognition applications, the latency is an important issue. We have developed a character-level incremental speech recognition (ISR) system that responds quickly even during the speech, where the hypotheses are…

Inverse Text Normalization (ITN) is crucial for converting spoken Automatic Speech Recognition (ASR) outputs into well-formatted written text, enhancing both readability and usability. Despite its importance, the integration of streaming…

The prediction of high-resolution hourly traffic volumes of a given roadway is essential for transportation planning. Traditionally, Automatic Traffic Recorders (ATR) are used to collect this hourly volume data. These large datasets are…