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

arXiv: https://arxiv.org/abs/2110.04410 · HTML: https://mlsanity.com/paper/2110.04410/

## Key facts

- Cited by 62 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Oct 2021.

## Built on by (most cited first, 30 of 62)

- [Koel-TTS: Enhancing LLM based Speech Generation with Preference Alignment and Classifier Free Guidance](https://mlsanity.com/paper/2502.05236/) (2025)
- [NanoCodec: Towards High-Quality Ultra Fast Speech LLM Inference](https://mlsanity.com/paper/2508.05835/) (2025)
- [People are poorly equipped to detect AI-powered voice clones](https://mlsanity.com/paper/2410.03791/) (2024)
- [Multi-scale Speaker Diarization with Dynamic Scale Weighting](https://mlsanity.com/paper/2203.15974/) (2022)
- [DiffAR: Denoising Diffusion Autoregressive Model for Raw Speech Waveform Generation](https://mlsanity.com/paper/2310.01381/) (2023)
- [Look Once to Hear: Target Speech Hearing with Noisy Examples](https://mlsanity.com/paper/2405.06289/) (2024)
- [Single and Multi-Speaker Cloned Voice Detection: From Perceptual to Learned Features](https://mlsanity.com/paper/2307.07683/) (2023)
- [Conformer-based Target-Speaker Automatic Speech Recognition for Single-Channel Audio](https://mlsanity.com/paper/2308.05218/) (2023)
- [Adapter-Based Extension of Multi-Speaker Text-to-Speech Model for New Speakers](https://mlsanity.com/paper/2211.00585/) (2022)
- [Training-Free Deepfake Voice Recognition by Leveraging Large-Scale Pre-Trained Models](https://mlsanity.com/paper/2405.02179/) (2024)
- [Discrete Diffusion for Generative Modeling of Text-Aligned Speech Tokens](https://mlsanity.com/paper/2509.20060/) (2025)
- [USAT: A Universal Speaker-Adaptive Text-to-Speech Approach](https://mlsanity.com/paper/2404.18094/) (2024)
- [A Compact End-to-End Model with Local and Global Context for Spoken Language Identification](https://mlsanity.com/paper/2210.15781/) (2022)
- [SelfVC: Voice Conversion With Iterative Refinement using Self Transformations](https://mlsanity.com/paper/2310.09653/) (2023)
- [Vibravox: A Dataset of French Speech Captured with Body-conduction Audio Sensors](https://mlsanity.com/paper/2407.11828/) (2024)
- [A Multi-Purpose Audio-Visual Corpus for Multi-Modal Persian Speech Recognition: the Arman-AV Dataset](https://mlsanity.com/paper/2301.10180/) (2023)
- [Summary of the DISPLACE Challenge 2023 - DIarization of SPeaker and LAnguage in Conversational Environments](https://mlsanity.com/paper/2311.12564/) (2023)
- [MSA-ASR: Efficient Multilingual Speaker Attribution with frozen ASR Models](https://mlsanity.com/paper/2411.18152/) (2024)
- [The First VoicePrivacy Attacker Challenge](https://mlsanity.com/paper/2504.14183/) (2025)
- [Voice Cloning: Comprehensive Survey](https://mlsanity.com/paper/2505.00579/) (2025)
- [CASPER: A Large Scale Spontaneous Speech Dataset](https://mlsanity.com/paper/2506.00267/) (2025)
- [The Art of Deception: Robust Backdoor Attack using Dynamic Stacking of Triggers](https://mlsanity.com/paper/2401.01537/) (2024)
- [VoiceChat-TTS: A Low-Latency Continuous Speech Synthesis Model for Interactive Agents](https://mlsanity.com/paper/2608.13831/) (2026)
- [Multilingual Multiaccented Multispeaker TTS with RADTTS](https://mlsanity.com/paper/2301.10335/) (2023)
- [Residual Information in Deep Speaker Embedding Architectures](https://mlsanity.com/paper/2302.02742/) (2023)
- [VANI: Very-lightweight Accent-controllable TTS for Native and Non-native speakers with Identity Preservation](https://mlsanity.com/paper/2303.07578/) (2023)
- [End-to-End Integration of Speech Separation and Voice Activity Detection for Low-Latency Diarization of Telephone Conversations](https://mlsanity.com/paper/2303.12002/) (2023)
- [Evaluation of Speech Representations for MOS prediction](https://mlsanity.com/paper/2306.09979/) (2023)
- [Voice Morphing: Two Identities in One Voice](https://mlsanity.com/paper/2309.02404/) (2023)
- [Enhancing Out-of-Vocabulary Performance of Indian TTS Systems for Practical Applications through Low-Effort Data Strategies](https://mlsanity.com/paper/2407.13435/) (2024)

## 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.