Sorry, you need to enable JavaScript to visit this website.

Building multilingual and crosslingual models help bring different languages together in a language universal space. It allows models to share parameters and transfer knowledge across languages, enabling faster and better adaptation to a new language. These approaches are particularly useful for low resource languages. In this paper, we propose a phoneme-level language model that can be used multilingually and for crosslingual adaptation to a target language.

Categories:
24 Views

The traditional method of pretraining neural acoustic models in low-resource languages consists of initializing the acoustic model parameters with a large, annotated multilingual corpus and can be a drain on time and resources. In an attempt to reuse TDNN-LSTMs already pre-trained using multilingual training, we have applied Teacher-Student (TS) learning as a method of pretraining to transfer knowledge from a multilingual TDNN-LSTM to a TDNN. The pretraining time is reduced by an order of magnitude with the use of language-specific data during the teacher-student training.

Categories:
47 Views

The task of automatic language identification (LID) involving multiple dialects of the same language family on short speech recordings is a challenging problem. This can be further complicated for short-duration audio snippets in the presence of noise sources. In these scenarios, the identity of the language/dialect may be reliably present only in parts of the speech embedded in the temporal sequence.

Categories:
21 Views

Code Switching refers to the phenomenon of changing languages within a sentence or discourse, and it represents a challenge for conventional automatic speech recognition systems deployed to tackle a single target language. The code switching problem is complicated by the lack of multi-lingual training data needed to build new and ad hoc multi-lingual acoustic and language models. In this work, we present a prototype research code-switching speech recognition system that leverages existing monolingual acoustic and language models, i.e., no ad hoc training is needed.

Categories:
82 Views

In many scenarios of a language identification task, the user will specify a small set of languages which he/she can speak instead of a large set of all possible languages. We want to model such prior knowledge into the way we train our neural networks, by replacing the commonly used softmax loss function with a novel loss function named tuplemax loss. As a matter of fact, a typical language identification system launched in North America has about 95% users who could speak no more than two languages.

Categories:
29 Views

Training a conventional automatic speech recognition (ASR) system to support multiple languages is challenging because the subword unit, lexicon and word inventories are typically language specific. In contrast, sequence-to-sequence models are well suited for multilingual ASR because they encapsulate an acoustic, pronunciation and language model jointly in a single network. In this work we present a single sequence-to-sequence ASR model trained on 9 different Indian languages, which have very little overlap in their

Categories:
9 Views

Techniques for multi-lingual and cross-lingual speech recognition can help in low resource scenarios, to bootstrap systems and enable analysis of new languages and domains. End-to-end approaches, in particular sequence-based techniques, are attractive because of their simplicity and elegance. While it is possible to integrate traditional multi-lingual bottleneck feature extractors as front-ends, we show that end-to-end multi-lingual training of sequence models is effective on context independent models trained using Connectionist Temporal Classification (CTC) loss.

Categories:
10 Views

A novel learnable dictionary encoding layer is proposed in this paper for end-to-end language identification. It is inline with the conventional GMM i-vector approach both theoretically and practically. We imitate the mechanism of traditional GMM training and Supervector encoding procedure on the top of CNN. The proposed layer can accumulate high-order statistics from variable-length input sequence and generate an utterance level fixed-dimensional vector representation.

Categories:
10 Views

Pages