# The tttAI System for the TSA-ASR Task of the SmartGlasses Challenge 2026

arXiv: https://arxiv.org/abs/2607.17867 · HTML: https://mlsanity.com/paper/2607.17867/

## Key facts

- No citing papers in the map yet (data through 19 Oct 2026).
- Placed in Speaker recognition and diarization, one of 11 directions in Speech and audio language models.
- Builds on 18 of its 21 references that are in the map.
- First posted on arXiv 20 Jul 2026.

## Placed in

- Speech and audio language models / [Speaker recognition and diarization](https://mlsanity.com/speech/speaker-recognition-and-diarization/)

## Builds on (most cited first, 18 of 18)

- [Conformer: Convolution-augmented Transformer for Speech Recognition](https://mlsanity.com/paper/2005.08100/) (2020)
- [WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing](https://mlsanity.com/paper/2110.13900/) (2021)
- [Qwen3-ASR Technical Report](https://mlsanity.com/paper/2601.21337/) (2026)
- [M2MeT: The ICASSP 2022 Multi-Channel Multi-Party Meeting Transcription Challenge](https://mlsanity.com/paper/2110.07393/) (2021)
- [End-to-End Neural Speaker Diarization with Self-attention](https://mlsanity.com/paper/1909.06247/) (2019)
- [Spot the conversation: speaker diarisation in the wild](https://mlsanity.com/paper/2007.01216/) (2020)
- [AISHELL-4: An Open Source Dataset for Speech Enhancement, Separation, Recognition and Speaker Diarization in Conference Scenario](https://mlsanity.com/paper/2104.03603/) (2021)
- [The Third DIHARD Diarization Challenge](https://mlsanity.com/paper/2012.01477/) (2020)
- [Music Source Separation with Band-split RNN](https://mlsanity.com/paper/2209.15174/) (2022)
- [Open Source MagicData-RAMC: A Rich Annotated Mandarin Conversational(RAMC) Speech Dataset](https://mlsanity.com/paper/2203.16844/) (2022)
- [NOTSOFAR-1 Challenge: New Datasets, Baseline, and Tasks for Distant Meeting Transcription](https://mlsanity.com/paper/2401.08887/) (2024)
- [Encoder-Decoder Based Attractors for End-to-End Neural Diarization](https://mlsanity.com/paper/2106.10654/) (2021)
- [MeetEval: A Toolkit for Computation of Word Error Rates for Meeting Transcription Systems](https://mlsanity.com/paper/2307.11394/) (2023)
- [Leveraging Self-Supervised Learning for Speaker Diarization](https://mlsanity.com/paper/2409.09408/) (2024)
- [FireRedASR2S: A State-of-the-Art Industrial-Grade All-in-One Automatic Speech Recognition System](https://mlsanity.com/paper/2603.10420/) (2026)
- [Fine-tune Before Structured Pruning: Towards Compact and Accurate Self-Supervised Models for Speaker Diarization](https://mlsanity.com/paper/2505.24111/) (2025)
- [Summary on The Multilingual Conversational Speech Language Model Challenge: Datasets, Tasks, Baselines, and Methods](https://mlsanity.com/paper/2509.13785/) (2025)
- [WeSep: A Scalable and Flexible Toolkit Towards Generalizable Target Speaker Extraction](https://mlsanity.com/paper/2409.15799/) (2024)

## Abstract (arXiv)

This paper presents the tttAI system submitted to the TSA-ASR task of the SmartGlasses Challenge 2026, evaluated on both two-person dialogues (Track 1) and multi-party meetings (Track 2). The task requires time-stamped speaker-attributed speech recognition from smart-glasses recordings. This is particularly challenging due to long-form audio, multiple speakers, and frequent overlapping speech. We proposed a cascaded architecture consisting of speaker diarization, overlap detection, target-speaker extraction, post-processing, and automatic speech recognition. The diarization module extracts features via WavLM-Large, performs frame-wise speaker classification with a Conformer encoder, and then generates global speaker segments through embedding clustering. For overlapped regions, we apply a WeSep-based target-speaker extraction model with ECAPA-TDNN speaker embeddings. When the extraction is unreliable, a dominant-speaker fallback strategy is used. The final system uses FireRedASR2-AED with the first microphone channel. The submitted system has a total parameter count of approximately 1.53B. On Track 1, our system achieves a tcpCER of 7.10%. On Track 2, it achieves a tcpCER of 34.04% and ranks second on the leaderboard.