We describe the latest version of Microsoft's conversational speech recognition system for
the Switchboard and CallHome domains. The system adds a CNN-BLSTM acoustic model to …

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 …

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 a human …

Training neural network acoustic models with sequencediscriminative criteria, such as state-
level minimum Bayes risk (sMBR), been shown to produce large improvements in …

We investigate back-propagation based sequence training of Context-Dependent Deep-
Neural-Network HMMs, or CD-DNN-HMMs, for conversational speech transcription …

Metaheuristic optimization algorithms play a crucial role in optimization problems. However,
the traditional identification methods have the following problems:(1) difficulties in nonlinear …

Detecting automatic speech recognition (ASR) errors can play an important role for effective
human-computer spoken dialogue system, as recognition errors can hinder accurate system …

A recurrent neural network language model (RNN-LM) can use a long word context more
than can an n-gram language model, and its effective has recently been shown in its …

We describe a simple but effective way of using multi-frame targets to improve the accuracy
of Artificial Neural Network-Hidden Markov Model (ANN-HMM) hybrid systems. In this …