Achieving Human Parity in Conversational Speech Recognition
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% for the Switchboard portion of the data, in which newly acquainted pairs of people discuss an assigned topic, and 11.3% for 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% and 11.0%, respectively. The key to our system's performance is the use of various 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.
Code (0)
등록된 구현이 없습니다.
Tasks
Language ModelingLanguage Modellingspeech-recognitionSpeech RecognitionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
VAIS ASR: Building a conversational speech recognition system using language model combination
Automatic Speech Recognition (ASR) systems have been evolving quickly and reaching human parity in certain cases. The systems usually perform pretty well on reading style and clean speech, however, most of the available …
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Language ModelingLanguage Modelling+2The CAPIO 2017 Conversational Speech Recognition System
In this paper we show how we have achieved the state-of-the-art performance on the industry-standard NIST 2000 Hub5 English evaluation set. We explore densely connected LSTMs, inspired by the densely connected convolutio…
image-classificationImage Classificationspeech-recognitionSpeech RecognitionEnglish Broadcast News Speech Recognition by Humans and Machines
With recent advances in deep learning, considerable attention has been given to achieving automatic speech recognition performance close to human performance on tasks like conversational telephone speech (CTS) recognitio…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech RecognitionSuper-Human Performance in Online Low-latency Recognition of Conversational Speech
Achieving super-human performance in recognizing human speech has been a goal for several decades, as researchers have worked on increasingly challenging tasks. In the 1990's it was discovered, that conversational speech…
DecoderGLM-4-Voice: Towards Intelligent and Human-Like End-to-End Spoken Chatbot
We introduce GLM-4-Voice, an intelligent and human-like end-to-end spoken chatbot. It supports both Chinese and English, engages in real-time voice conversations, and varies vocal nuances such as emotion, intonation, spe…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)ChatbotLanguage Modeling+6