Achieving Human Parity in Conversational Speech Recognition

by   W. Xiong, et al.

Conversational speech recognition has served as a flagship speech recognition task since the release of the Switchboard corpus in the 1990s. In this paper, we measure the human error rate on the widely used NIST 2000 test set, and find that our latest automated system has reached human parity. The error rate of professional transcribers is 5.9 which newly acquainted pairs of people discuss an assigned topic, and 11.3 the CallHome portion where friends and family members have open-ended conversations. In both cases, our automated system establishes a new state of the art, and edges past the human benchmark, achieving error rates of 5.8 11.0 convolutional and LSTM acoustic model architectures, combined with a novel spatial smoothing method and lattice-free MMI acoustic training, multiple recurrent neural network language modeling approaches, and a systematic use of system combination.


page 1

page 2

page 3

page 4


The Microsoft 2016 Conversational Speech Recognition System

We describe Microsoft's conversational speech recognition system, in whi...

The CAPIO 2017 Conversational Speech Recognition System

In this paper we show how we have achieved the state-of-the-art performa...

The Microsoft 2017 Conversational Speech Recognition System

We describe the 2017 version of Microsoft's conversational speech recogn...

The Marchex 2018 English Conversational Telephone Speech Recognition System

In this paper, we describe recent improvements to the production Marchex...

The IBM 2016 English Conversational Telephone Speech Recognition System

We describe a collection of acoustic and language modeling techniques th...

ASAPP-ASR: Multistream CNN and Self-Attentive SRU for SOTA Speech Recognition

In this paper we present state-of-the-art (SOTA) performance on the Libr...

The People's Speech: A Large-Scale Diverse English Speech Recognition Dataset for Commercial Usage

The People's Speech is a free-to-download 30,000-hour and growing superv...

Please sign up or login with your details

Forgot password? Click here to reset