Extending multilingual automatic speech recognition (mASR) systems to new languages poses challenges, particularly when training data for existing languages is limited or unavailable. To tackle this issue, we suggest utilizing supplementary encoder and decoder components. Specifically, we propose appending and fine-tuning a distinct decoder designed for new languages, while preserving the parameters of existing languages to minimize disruption to their performance. Furthermore, we advocate attaching an additional encoder component to enhance acoustic representation learning for new languages, resulting in substantial improvements in word error rate performance. Our experimental findings demonstrate the effectiveness of the proposed methods for the task of extending language support within mASR systems.

One of limitations in end-to-end automatic speech recognition (ASR) framework is its performance would be compromised if train-test utterance lengths are mismatched.In this paper, we propose an on-the-fly random utterance concatenation (RUC) based data augmentation method to alleviate train-test utterance length mismatch issue for short-video ASR task.Specifically, we are motivated by observations that our human-transcribed training utterances tend to be much shorter for short-video spontaneous speech (∼3 seconds on average), while our test utterance generated from voice activity detection front-end is much longer (∼10 seconds on average).Such a mismatch can lead to suboptimal performance.Empirically, it's observed the proposed RUC method significantly improves long utterance recognition without performance drop on short one.Overall, it achieves 5.72% word error rate reduction on average for 15 languages and improved robustness to various utterance length.

In this paper, we propose the use of distance and co-occurrence information of word-pairs to improve language modeling. We have empirically shown that, for history-context sizes of up to ten words, the extracted information about distance and co-occurrence complements the n-gram language model well, for which learning long-history contexts is inherently difficult. Evaluated on the Wall Street Journal and the Switchboard corpora, our proposed model reduces the trigram model perplexity by up to 11.2% and 6.5%, respectively. As compared to the distant bigram model and the trigger model, our proposed model offers a more effective manner of capturing far context information, as verified in terms of perplexity and computational efficiency, i.e., fewer free parameters to be fine-tuned. Experiments using the proposed model for speech recognition, text classification and word prediction tasks showed improved performance.

This paper reports our study in exploiting the distance and co-occurrence information of word-pairs to improve the n-gram language model. We used these two types of information for modeling the distant context, up to history length of ten. Also we show that the proposed model provides complementary information about the n-gram's context that is unable to be captured by the n-gram model due to data scarcity. Evaluated on the WSJ and SWB-1 corpora, the proposed model reduced the trigram perplexity up to 11.2% and 6.5% respectively. In an N-best re-ranking task of the Aurora-4 database, our model aided a hexagram model to perform ~9% relatively better in terms of WER.

Biometric characteristics cannot be changed; therefore, the loss of privacy is permanent if they are ever compromised. This paper presents a two-factor cancelable formulation, where the biometric data are distorted in a revocable but non-reversible manner by first transforming the raw biometric data into a fixed-length feature vector and then projecting the feature vector onto a sequence of random subspaces that were derived from a user-specific pseudorandom number (PRN). This process is revocable and makes replacing biometrics as easy as replacing PRNs. The formulation has been verified under a number of scenarios (normal, stolen PRN, and compromised biometrics scenarios) using 2400 Facial Recognition Technology face images. The diversity property is also examined.