mlsanityData to 13 Oct 2026

A Compact End-to-End Model with Local and Global Context for Spoken Language Identification

arXiv 2210.15781 ↗First posted 27 Oct 2022eess.AS cs.CL cs.SDcited by 4

Not on the map. Why?

Abstract (arXiv)

We introduce TitaNet-LID, a compact end-to-end neural network for Spoken Language Identification (LID) that is based on the ContextNet architecture. TitaNet-LID employs 1D depth-wise separable convolutions and Squeeze-and-Excitation layers to effectively capture local and global context within an utterance. Despite its small size, TitaNet-LID achieves performance similar to state-of-the-art models on the VoxLingua107 dataset while being 10 times smaller. Furthermore, it can be easily adapted to new acoustic conditions and unseen languages through simple fine-tuning, achieving a state-of-the-art accuracy of 88.2% on the FLEURS benchmark. Our model is scalable and can achieve a better trade-off between accuracy and speed. TitaNet-LID performs well even on short utterances less than 5s in length, indicating its robustness to input length.

Key facts. Cited by 4 papers in the map (data through 13 Oct 2026). Builds on 20 of its 34 references that are in the map. First posted on arXiv 27 Oct 2022.

Builds on

20 of 34 references.

References · 20

  1. 2017Squeeze-and-Excitation Networkscited by 4,772
  2. 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 1,844
  3. 2019SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognitioncited by 1,359
  4. 2020ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verificationcited by 612
  5. 2021XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scalecited by 594
  6. 2022FLEURS: Few-shot Learning Evaluation of Universal Representations of Speechcited by 459
  7. 2021SpeechBrain: A General-Purpose Speech Toolkitcited by 404
  8. 2019NeMo: a toolkit for building AI applications using Neural Modulescited by 232
  9. 2020VoxLingua107: a Dataset for Spoken Language Recognitioncited by 119
  10. 2020ContextNet: Improving Convolutional Neural Networks for Automatic Speech Recognition with Global Contextcited by 96
  11. 2019QuartzNet: Deep Automatic Speech Recognition with 1D Time-Channel Separable Convolutionscited by 93
  12. 2021TitaNet: Neural Model for speaker representation with 1D Depth-wise separable convolutions and global contextcited by 61
8 more
  1. 2018Exploring the Encoding Layer and Loss Function in End-to-End Speaker and Language Recognition Systemcited by 45
  2. 2021Citrinet: Closing the Gap between Non-Autoregressive and Autoregressive End-to-End Models for Automatic Speech Recognitioncited by 33
  3. 2022XTREME-S: Evaluating Cross-lingual Speech Representationscited by 22
  4. 2022Improving Language Identification of Accented Speechcited by 10
  5. 2022ConvRNN-T: Convolutional Augmented Recurrent Neural Network Transducers for Streaming Speech Recognitioncited by 8
  6. 2022PHO-LID: A Unified Model Incorporating Acoustic-Phonetic and Phonotactic Information for Language Identificationcited by 5
  7. 2019Utterance-level end-to-end language identification using attention-based CNN-BLSTMcited by 4
  8. 2022Transducer-based language embedding for spoken language identificationcited by 2

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2024: 2; 2025: 1; 2026: 1.

4 papers.

  1. 2024Exploring Spoken Language Identification Strategies for Automatic Transcription of Multilingual Broadcast and Institutional Speechcited by 0
  2. 2024Exploring the Impact of Data Quantity on ASR in Extremely Low-resource Languagescited by 0
  3. 2025Geolocation-Aware Robust Spoken Language Identificationcited by 0
  4. 2026Acoustic domain shift in spoken language identification from systematic domain generalization evaluation to real-world applicationcited by 0