Related papers: Automatic speech recognition for launch control ce…
Automatic recognition of disordered speech remains a highly challenging task to date due to data scarcity. This paper presents a reinforcement learning (RL) based on-the-fly data augmentation approach for training state-of-the-art PyChain…
Recent success of the Tacotron speech synthesis architecture and its variants in producing natural sounding multi-speaker synthesized speech has raised the exciting possibility of replacing expensive, manually transcribed, domain-specific,…
Recent advancements in machine learning have significantly improved speech recognition, but recognizing speech from non-fluent or accented speakers remains a challenge. Previous efforts, relying on rule-based pronunciation patterns, have…
Neural models have become ubiquitous in automatic speech recognition systems. While neural networks are typically used as acoustic models in more complex systems, recent studies have explored end-to-end speech recognition systems based on…
Speaker recognition, recognizing speaker identities based on voice alone, enables important downstream applications, such as personalization and authentication. Learning speaker representations, in the context of supervised learning,…
Supervised speech enhancement relies on parallel databases of degraded speech signals and their clean reference signals during training. This setting prohibits the use of real-world degraded speech data that may better represent the…
In this work we explored building automatic speech recognition models for transcribing doctor patient conversation. We collected a large scale dataset of clinical conversations ($14,000$ hr), designed the task to represent the real word…
Automatic speech recognition models are often adapted to improve their accuracy in a new domain. A potential drawback of model adaptation to new domains is catastrophic forgetting, where the Word Error Rate on the original domain is…
The conversion from text to speech relies on the accurate mapping from linguistic to acoustic symbol sequences, for which current practice employs recurrent statistical models like recurrent neural networks. Despite the good performance of…
Building conversational speech recognition systems for new languages is constrained by the availability of utterances that capture user-device interactions. Data collection is both expensive and limited by the speed of manual transcription.…
Recently, there has been growth in providers of speech transcription services enabling others to leverage technology they would not normally be able to use. As a result, speech-enabled solutions have become commonplace. Their success…
Neural transducers have achieved human level performance on standard speech recognition benchmarks. However, their performance significantly degrades in the presence of cross-talk, especially when the primary speaker has a low…
The recent developments in technology have re-warded us with amazing audio synthesis models like TACOTRON and WAVENETS. On the other side, it poses greater threats such as speech clones and deep fakes, that may go undetected. To tackle…
Speech signals, typically sampled at rates in the tens of thousands per second, contain redundancies, evoking inefficiencies in sequence modeling. High-dimensional speech features such as spectrograms are often used as the input for the…
Data augmentation has proven to be a promising prospect in improving the performance of deep learning models by adding variability to training data. In previous work with developing a noise robust acoustic-to-articulatory speech inversion…
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…
This paper introduces a convolutional recurrent network with attention for speech command recognition. Attention models are powerful tools to improve performance on natural language, image captioning and speech tasks. The proposed model…
Despite recent advances, Automatic Speech Recognition (ASR) systems are still far from perfect. Typical errors include acronyms, named entities, and domain-specific special words for which little or no labeled data is available. To address…
Speech recognizers trained on close-talking speech do not generalize to distant speech and the word error rate degradation can be as large as 40% absolute. Most studies focus on tackling distant speech recognition as a separate problem,…
Teleconferencing is becoming essential during the COVID-19 pandemic. However, in real-world applications, speech quality can deteriorate due to, for example, background interference, noise, or reverberation. To solve this problem, target…