Although Long-Short Term Memory (LSTM) networks and deep Transformers are now
extensively used in offline ASR, it is unclear how best offline systems can be adapted to …

Spoken term detection (STD) aims at retrieving data from a speech repository given a textual
representation of the search term. Nowadays, it is receiving much interest due to the large …

This paper reports on the setup and evaluation of robust speech recognition system parts,
geared towards transcript generation for heterogeneous, real-life media collections. The …

Many applications use sequences of n consecutive symbols (n-grams). Hashing these n-
grams can be a performance bottleneck. For more speed, recursive hash families compute …

This paper describes a Broadcast News (BN) database called Transcrigal-DB. The news
shows are mainly in Galician language, although around 11% of data is in Spanish. This …

摘要针对基于动态解码网络的大词汇量连续语音识别器, 本文提出了一种采用扩展N
元文法模型进行快速语言模型(Language model, LM) 预测的方法. 扩展N …

Recently, minimum perfect hashing (MPH)-based language model (LM) lookup methods
have been proposed for fast access of N-gram LM scores in lexical-tree based LVCSR …

In distributed speech recognition, speech feature vectors are obtained at the client side, and
transmitted to the remote server for recognition. In this paper, we investigate the robustness …

The paper describes our current work on speech-to-text transcription for recordings in two
languages. The experimental framework consists of television news shows in Galician and …

In this paper, an efficient method for language model look-ahead probability generation is
presented. Traditional methods generate language model look-ahead (LMLA) probabilities …