English
Related papers

Related papers: Improving Transducer-Based Spoken Language Underst…

200 papers

Recently, end-to-end models have been widely used in automatic speech recognition (ASR) systems. Two of the most representative approaches are connectionist temporal classification (CTC) and attention-based encoder-decoder (AED) models.…

Computation and Language · Computer Science 2023-04-18 Ruchao Fan , Wei Chu , Peng Chang , Abeer Alwan

Recent research shows end-to-end ASR systems can recognize overlapped speech from multiple speakers. However, all published works have assumed no latency constraints during inference, which does not hold for most voice assistant…

Audio and Speech Processing · Electrical Eng. & Systems 2021-02-22 Ilya Sklyar , Anna Piunova , Yulan Liu

Spoken language understanding (SLU) systems extract transcriptions, as well as semantics of intent or named entities from speech, and are essential components of voice activated systems. SLU models, which either directly extract semantics…

Computation and Language · Computer Science 2021-02-16 Milind Rao , Pranav Dheram , Gautam Tiwari , Anirudh Raju , Jasha Droppo , Ariya Rastrow , Andreas Stolcke

This paper addresses end-to-end automatic speech recognition (ASR) for long audio recordings such as lecture and conversational speeches. Most end-to-end ASR models are designed to recognize independent utterances, but contextual…

Computation and Language · Computer Science 2021-04-20 Takaaki Hori , Niko Moritz , Chiori Hori , Jonathan Le Roux

End-to-end (E2E) automatic speech recognition models like Recurrent Neural Networks Transducer (RNN-T) are becoming a popular choice for streaming ASR applications like voice assistants. While E2E models are very effective at learning…

Computation and Language · Computer Science 2022-01-12 Chhavi Choudhury , Ankur Gandhe , Xiaohan Ding , Ivan Bulyko

Spoken Language Understanding (SLU) aims to extract structured semantic representations (e.g., slot-value pairs) from speech recognized texts, which suffers from errors of Automatic Speech Recognition (ASR). To alleviate the problem caused…

Computation and Language · Computer Science 2020-09-08 Chen Liu , Su Zhu , Lu Chen , Kai Yu

The two most popular loss functions for streaming end-to-end automatic speech recognition (ASR) are RNN-Transducer (RNN-T) and connectionist temporal classification (CTC). Between these two loss types we can classify the monotonic RNN-T…

Audio and Speech Processing · Electrical Eng. & Systems 2022-10-25 Niko Moritz , Frank Seide , Duc Le , Jay Mahadeokar , Christian Fuegen

In recent years, end-to-end speech recognition has emerged as a technology that integrates the acoustic, pronunciation dictionary, and language model components of the traditional Automatic Speech Recognition model. It is possible to…

Computation and Language · Computer Science 2023-12-18 Tzu-Ting Yang , Hsin-Wei Wang , Berlin Chen

All-neural end-to-end (E2E) automatic speech recognition (ASR) systems that use a single neural network to transduce audio to word sequences have been shown to achieve state-of-the-art results on several tasks. In this work, we examine the…

Audio and Speech Processing · Electrical Eng. & Systems 2019-10-28 Arun Narayanan , Rohit Prabhavalkar , Chung-Cheng Chiu , David Rybach , Tara N. Sainath , Trevor Strohman

Understanding spoken language is a highly complex problem, which can be decomposed into several simpler tasks. In this paper, we focus on Spoken Language Understanding (SLU), the module of spoken dialog systems responsible for extracting a…

Computation and Language · Computer Science 2017-06-22 Marco Dinarelli , Yoann Dupont , Isabelle Tellier

The requirements for many applications of state-of-the-art speech recognition systems include not only low word error rate (WER) but also low latency. Specifically, for many use-cases, the system must be able to decode utterances in a…

The acoustic and linguistic features are important cues for the spoken language identification (LID) task. Recent advanced LID systems mainly use acoustic features that lack the usage of explicit linguistic feature encoding. In this paper,…

Computation and Language · Computer Science 2022-08-01 Peng Shen , Xugang Lu , Hisashi Kawai

ASR systems designed for native English (L1) usually underperform on non-native English (L2). To address this performance gap, \textbf{(i)} we extend our previous work to investigate fine-tuning of a pre-trained wav2vec 2.0 model…

Computation and Language · Computer Science 2022-02-11 Peter Sullivan , Toshiko Shibano , Muhammad Abdul-Mageed

End-to-end (E2E) automatic speech recognition (ASR) models have recently demonstrated superior performance over the traditional hybrid ASR models. Training an E2E ASR model requires a large amount of data which is not only expensive but may…

Machine Learning · Computer Science 2021-06-16 Amin Fazel , Wei Yang , Yulan Liu , Roberto Barra-Chicote , Yixiong Meng , Roland Maas , Jasha Droppo

We introduce a text-to-speech(TTS) framework based on a neural transducer. We use discretized semantic tokens acquired from wav2vec2.0 embeddings, which makes it easy to adopt a neural transducer for the TTS framework enjoying its monotonic…

Audio and Speech Processing · Electrical Eng. & Systems 2023-11-09 Minchan Kim , Myeonghun Jeong , Byoung Jin Choi , Dongjune Lee , Nam Soo Kim

Comprehending the overall intent of an utterance helps a listener recognize the individual words spoken. Inspired by this fact, we perform a novel study of the impact of explicitly incorporating intent representations as additional…

Audio and Speech Processing · Electrical Eng. & Systems 2022-02-22 Swayambhu Nath Ray , Minhua Wu , Anirudh Raju , Pegah Ghahremani , Raghavendra Bilgi , Milind Rao , Harish Arsikere , Ariya Rastrow , Andreas Stolcke , Jasha Droppo

The paper describes the BUT's speech translation systems. The systems are English$\longrightarrow$German offline speech translation systems. The systems are based on our previous works \cite{Jointly_trained_transformers}. Though End-to-End…

Computation and Language · Computer Science 2020-10-23 Hari Krishna Vydana , Lukas Burget , Jan Cernocky

Neural transducer (RNNT)-based target-speaker speech recognition (TS-RNNT) directly transcribes a target speaker's voice from a multi-talker mixture. It is a promising approach for streaming applications because it does not incur the extra…

Audio and Speech Processing · Electrical Eng. & Systems 2023-05-26 Takafumi Moriya , Hiroshi Sato , Tsubasa Ochiai , Marc Delcroix , Takanori Ashihara , Kohei Matsuura , Tomohiro Tanaka , Ryo Masumura , Atsunori Ogawa , Taichi Asami

Self-supervised learning (SSL) is a powerful tool that allows learning of underlying representations from unlabeled data. Transformer based models such as wav2vec 2.0 and HuBERT are leading the field in the speech domain. Generally these…

Computation and Language · Computer Science 2022-02-08 Bethan Thomas , Samuel Kessler , Salah Karout

Personal rare word recognition in end-to-end Automatic Speech Recognition (E2E ASR) models is a challenge due to the lack of training data. A standard way to address this issue is with shallow fusion methods at inference time. However, due…