Related papers: Towards Maximum Likelihood Training for Transducer…
Consistency regularization is a commonly used practice to encourage the model to generate consistent representation from distorted input features and improve model generalization. It shows significant improvement on various speech…
With increasingly more powerful compute capabilities and resources in today's devices, traditionally compute-intensive automatic speech recognition (ASR) has been moving from the cloud to devices to better protect user privacy. However, it…
User studies have shown that reducing the latency of our simultaneous lecture translation system should be the most important goal. We therefore have worked on several techniques for reducing the latency for both components, the automatic…
Streaming automatic speech recognition (ASR) is very important for many real-world ASR applications. However, a notable challenge for streaming ASR systems lies in balancing operational performance against latency constraint. Recently, a…
This paper presents a novel optimization framework for automatic speech recognition (ASR) with the aim of reducing hallucinations produced by an ASR model. The proposed framework optimizes the ASR model to maximize an expected factual…
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…
Automatic speech recognition (ASR) with an encoder equipped with self-attention, whether streaming or non-streaming, takes quadratic time in the length of the speech utterance. This slows down training and decoding, increase their cost, and…
History and future contextual information are known to be important for accurate acoustic modeling. However, acquiring future context brings latency for streaming ASR. In this paper, we propose a new framework - Chunking, Simulating Future…
Speaker change detection (SCD) is an important feature that improves the readability of the recognized words from an automatic speech recognition (ASR) system by breaking the word sequence into paragraphs at speaker change points. Existing…
We extend the frameworks of Serialized Output Training (SOT) to address practical needs of both streaming and offline automatic speech recognition (ASR) applications. Our approach focuses on balancing latency and accuracy, catering to…
Deep biasing for the Transducer can improve the recognition performance of rare words or contextual entities, which is essential in practical applications, especially for streaming Automatic Speech Recognition (ASR). However, deep biasing…
Joint optimization of multi-channel front-end and automatic speech recognition (ASR) has attracted much interest. While promising results have been reported for various tasks, past studies on its meeting transcription application were…
In a pipeline speech translation system, automatic speech recognition (ASR) system will transmit errors in recognition to the downstream machine translation (MT) system. A standard machine translation system is usually trained on parallel…
Human language is a combination of elemental languages/domains/styles that change across and sometimes within discourses. Language models, which play a crucial role in speech recognizers and machine translation systems, are particularly…
The neural transducer is an end-to-end model for automatic speech recognition (ASR). While the model is well-suited for streaming ASR, the training process remains challenging. During training, the memory requirements may quickly exceed the…
Automatic speech recognition (ASR) systems, increasingly prevalent in education, healthcare, employment, and mobile technology, face significant challenges in inclusivity, particularly for the 80 million-strong global community of people…
End-to-end speech recognition is a promising technology for enabling compact automatic speech recognition (ASR) systems since it can unify the acoustic and language model into a single neural network. However, as a drawback, training of…
Streaming neural network models for fast frame-wise responses to various speech and sensory signals are widely adopted on resource-constrained platforms. Hence, increasing the learning capacity of such streaming models (i.e., by adding more…
End-to-end (E2E) automatic speech recognition (ASR) can operate in two modes: streaming and non-streaming, each with its pros and cons. Streaming ASR processes the speech frames in real-time as it is being received, while non-streaming ASR…
This paper studies a novel pre-training technique with unpaired speech data, Speech2C, for encoder-decoder based automatic speech recognition (ASR). Within a multi-task learning framework, we introduce two pre-training tasks for the…