Spoken Language Recognition using X-vectors

By David Snyder, Daniel Garcia-Romero, Alan McCree, Gregory Sell, Daniel Povey, Sanjeev Khudanpur. 2018

246 citations recorded by the source corpus.

In this paper, we apply x-vectors to the task of spoken language recognition. This framework consists of a deep neural network that maps sequences of speech features to fixed-dimensional embeddings, called x-vectors. Long-term language characteristics are captured in the network by a temporal pooling layer that aggregates information across time. Once extracted, x-vectors utilize the same classification technology developed for i-vectors. In the 2017 NIST language recognition evaluation, x-vectors achieved excellent results and outperformed our state-of-the-art i-vector systems. In the post-evaluation analysis presented here, we experiment with several variations of the x-vector framework, and find that the best performing system uses multilingual bottleneck features, data augmentation, and a discriminative Gaussian classifier.

Subfields: Artificial Intelligence, Speech & Audio, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Junichi Yamagishi
2. Erica Cooper
3. Yusuke Yasuda
4. Cheng-I Lai
5. Tanel Alumäe
6. Jörgen Valk
7. Xu Tan
8. Tao Qin

In Speech & Audio

1. Junichi Yamagishi
2. Erica Cooper
3. Tanel Alumäe
4. Jörgen Valk
5. Yusuke Yasuda
6. Cheng-I Lai
7. Xin Eric Wang

In Signal Processing

1. Junichi Yamagishi
2. Erica Cooper
3. Cheng-I Lai
4. Yusuke Yasuda
5. Tanel Alumäe
6. Jörgen Valk
7. Xu Tan
8. Tao Qin

Citations in the corpus

• VOXLINGUA107: A Dataset for Spoken Language Recognition (2020, methodology): “In all experiments, we use language embedding models derived from the x-vector paradigm [12, 13], with several enhancements.”
• Can Speaker Augmentation Improve Multi-Speaker End-to-End TTS? (2020, methodology): “ialect identification can be considered as a subtask of spoken language recognition, and in general, approaches from speaker recognition tasks can be directly transferred to dialect identification, see [24, 25, 26, 27]. Therefore, similar to our speaker encoder network, we reused the Learnable Diction”