# The CAPIO 2017 Conversational Speech Recognition System

Source: [The CAPIO 2017 Conversational Speech Recognition System](<https://www.sota2.com/research/paper/68fa64401e209131cea03766>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T20:59:11.405Z

Authors: Kyu J. Han, Akshay Chandrashekaran, Jungsuk Kim, Ian Lane

Published: 2017-12-29T23:31:05.000Z

## Abstract

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 convolutional networks recently introduced for image classification tasks. We also propose an acoustic model adaptation scheme that simply averages the parameters of a seed neural network acoustic model and its adapted version. This method was applied with the CallHome training corpus and improved individual system performances by on average 6.1% (relative) against the CallHome portion of the evaluation set with no performance loss on the Switchboard portion. With RNN-LM rescoring and lattice combination on the 5 systems trained across three different phone sets, our 2017 speech recognition system has obtained 5.0% and 9.1% on Switchboard and CallHome, respectively, both of which are the best word error rates reported thus far. According to IBM in their latest work to compare human and machine transcriptions, our reported Switchboard word error rate can be considered to surpass the human parity (5.1%) of transcribing conversational telephone speech.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Automatic Speech Recognition on LibriSpeech (dev-clean)](<https://www.sota2.com/research/sota/automatic-speech-recognition-on-librispeech-dev-clean.md>): Automatic Speech Recognition; LibriSpeech (dev-clean); WER (%): 2.6.

- [Automatic Speech Recognition on LibriSpeech (dev-other)](<https://www.sota2.com/research/sota/automatic-speech-recognition-on-librispeech-dev-other.md>): Automatic Speech Recognition; LibriSpeech (dev-other); WER: 7.56.

- [Automatic Speech Recognition on LibriSpeech clean (test)](<https://www.sota2.com/research/sota/automatic-speech-recognition-on-librispeech-clean-test.md>): Automatic Speech Recognition; LibriSpeech clean (test); WER: 3.19.

- [Automatic Speech Recognition on LibriSpeech (test-other)](<https://www.sota2.com/research/sota/automatic-speech-recognition-on-librispeech-test-other.md>): Automatic Speech Recognition; LibriSpeech (test-other); WER: 7.6.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1801.00059>)

[PDF](<https://arxiv.org/pdf/1801.00059.pdf>)
