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 …

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 a human error …

In this study, we investigate whether attention-based information flow inside large language
models (LLMs) is aggregated through noticeable patterns for long context processing. Our …

In this paper, we propose a deep convolutional neural network (CNN) with layer-wise context
expansion and location-based attention, for large vocabulary speech recognition. In our …

This paper presents Z-Code++, a new pre-trained language model optimized for abstractive
text summarization. The model extends the state of the art encoder-decoder model using …

This paper describes a system that generates speaker-annotated transcripts of meetings by
using a microphone array and a 360-degree camera. The hallmark of the system is its ability …

Unsupervised single-channel overlapped speech recognition is one of the hardest problems
in automatic speech recognition (ASR). Permutation invariant training (PIT) is a state of the …

In this study, we investigate whether attention-based information flow inside large language
models (LLMs) is aggregated through noticeable patterns for long context processing. Our …

The input and output of most text generation tasks can be transformed to two sequences of
tokens and they can be modeled using sequence-to-sequence learning modeling tools such …