Data to 7 Oct 2026

TitaNet: Neural Model for speaker representation with 1D Depth-wise separable convolutions and global context

arXiv 2110.04410 ↗First posted 8 Oct 2021eess.AS cs.SDcited by 61

Not on the map. Why?

Abstract (arXiv)

In this paper, we propose TitaNet, a novel neural network architecture for extracting speaker representations. We employ 1D depth-wise separable convolutions with Squeeze-and-Excitation (SE) layers with global context followed by channel attention based statistics pooling layer to map variable-length utterances to a fixed-length embedding (t-vector). TitaNet is a scalable architecture and achieves state-of-the-art performance on speaker verification task with an equal error rate (EER) of 0.68% on the VoxCeleb1 trial file and also on speaker diarization tasks with diarization error rate (DER) of 1.73% on AMI-MixHeadset, 1.99% on AMI-Lapel and 1.11% on CH109. Furthermore, we investigate various sizes of TitaNet and present a light TitaNet-S model with only 6M parameters that achieve near state-of-the-art results in diarization tasks.

Key facts. Cited by 61 papers in the map (data through 7 Oct 2026). First posted on arXiv 8 Oct 2021.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 4; 2023: 14; 2024: 14; 2025: 18; 2026: 11.

61 papers.

Sort:

By area:

2025Koel-TTS: Enhancing LLM based Speech Generation with Preference Alignment and Classifier Free Guidancecited by 26
2025NanoCodec: Towards High-Quality Ultra Fast Speech LLM Inferencecited by 14
2024People are poorly equipped to detect AI-powered voice clonescited by 12
2022Multi-scale Speaker Diarization with Dynamic Scale Weightingcited by 11
2023DiffAR: Denoising Diffusion Autoregressive Model for Raw Speech Waveform Generationcited by 11
2024Look Once to Hear: Target Speech Hearing with Noisy Examplescited by 11
2023Single and Multi-Speaker Cloned Voice Detection: From Perceptual to Learned Featurescited by 10
2023Conformer-based Target-Speaker Automatic Speech Recognition for Single-Channel Audiocited by 10
2022Adapter-Based Extension of Multi-Speaker Text-to-Speech Model for New Speakerscited by 9
2024Training-Free Deepfake Voice Recognition by Leveraging Large-Scale Pre-Trained Modelscited by 8
2025Discrete Diffusion for Generative Modeling of Text-Aligned Speech Tokenscited by 7
2024USAT: A Universal Speaker-Adaptive Text-to-Speech Approachcited by 6

38 more

2023SelfVC: Voice Conversion With Iterative Refinement using Self Transformationscited by 5
2024Vibravox: A Dataset of French Speech Captured with Body-conduction Audio Sensorscited by 5
2022A Compact End-to-End Model with Local and Global Context for Spoken Language Identificationcited by 4
2023A Multi-Purpose Audio-Visual Corpus for Multi-Modal Persian Speech Recognition: the Arman-AV Datasetcited by 4
2023Summary of the DISPLACE Challenge 2023 - DIarization of SPeaker and LAnguage in Conversational Environmentscited by 4
2024MSA-ASR: Efficient Multilingual Speaker Attribution with frozen ASR Modelscited by 4
2025The First VoicePrivacy Attacker Challengecited by 4
2025Voice Cloning: Comprehensive Surveycited by 4
2024The Art of Deception: Robust Backdoor Attack using Dynamic Stacking of Triggerscited by 3
2025CASPER: A Large Scale Spontaneous Speech Datasetcited by 3
2026VoiceChat-TTS: A Low-Latency Continuous Speech Synthesis Model for Interactive Agentscited by 3
2023Multilingual Multiaccented Multispeaker TTS with RADTTScited by 2
2023Residual Information in Deep Speaker Embedding Architecturescited by 2
2023VANI: Very-lightweight Accent-controllable TTS for Native and Non-native speakers with Identity Preservationcited by 2
2023End-to-End Integration of Speech Separation and Voice Activity Detection for Low-Latency Diarization of Telephone Conversationscited by 2
2023Evaluation of Speech Representations for MOS predictioncited by 2
2023Voice Morphing: Two Identities in One Voicecited by 2
2024Enhancing Out-of-Vocabulary Performance of Indian TTS Systems for Practical Applications through Low-Effort Data Strategiescited by 2
2024Character-aware audio-visual subtitling in contextcited by 2
2025An Exploration of Mamba for Speech Self-Supervised Modelscited by 2
2025Recent Trends in Distant Conversational Speech Recognition: A Review of CHiME-7 and 8 DASR Challengescited by 2
2024Investigating the Effects of Large-Scale Pseudo-Stereo Data and Different Speech Foundation Model on Dialogue Generative Spoken Language Modelcited by 1
2024Hypothesis Clustering and Merging: Novel MultiTalker Speech Recognition with Speaker Tokenscited by 1
2025Tessellated Linear Model for Age Prediction from Voicecited by 1
2025Sparse Autoencoder Insights on Voice Embeddingscited by 1
2025Speaker Retrieval in the Wild: Challenges, Effectiveness and Robustnesscited by 1
2025Universal Semantic Disentangled Privacy-preserving Speech Representation Learningcited by 1
2025Do We Still Need Audio? Rethinking Speaker Diarization with a Text-Based Approach Using Multiple Prediction Modelscited by 1
2025Align2Speak: Improving TTS for Low Resource Languages via ASR-Guided Online Preference Optimizationcited by 1
2026MagpieTTS-LF: Inference-Time Long-Form Speech Generation Without Training on Long-Form datacited by 1
2022A Comparison of Transformer, Convolutional, and Recurrent Neural Networks on Phoneme Recognitioncited by 0
2023Factors Affecting the Performance of Automated Speaker Verification in Alzheimer's Disease Clinical Trialscited by 0
2023Unified and Dynamic Graph for Temporal Character Grouping in Long Videoscited by 0
2024Speaker Tagging Correction With Non-Autoregressive Language Modelscited by 0
2024What happens to diffusion model likelihood when your model is conditional?cited by 0
2024The First VoicePrivacy Attacker Challenge Evaluation Plancited by 0
2025CoMuMDR: Code-mixed Multi-modal Multi-domain corpus for Discourse paRsing in conversationscited by 0
2025Evaluating Identity Leakage in Speaker De-Identification Systemscited by 0

50 most cited of 61 All 61 (JSON)