F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching

This paper introduces F5-TTS, a fully non-autoregressive text-to-speech system based on flow matching with Diffusion Transformer (DiT). Without requiring complex designs such as duration model, text encoder, and phoneme alignment, the text input is simply padded with filler tokens to the same length as input speech, and then the denoising is performed for speech generation, which was originally proved feasible by E2 TTS. However, the original design of E2 TTS makes it hard to follow due to its slow convergence and low robustness. To address these issues, we first model the input with ConvNeXt to refine the text representation, making it easy to align with the speech. We further propose an inference-time Sway Sampling strategy, which significantly improves our model's performance and efficiency. This sampling strategy for flow step can be easily applied to existing flow matching based models without retraining. Our design allows faster training and achieves an inference RTF of 0.15, which is greatly improved compared to state-of-the-art diffusion-based TTS models. Trained on a public 100K hours multilingual dataset, our Fairytaler Fakes Fluent and Faithful speech with Flow matching (F5-TTS) exhibits highly natural and expressive zero-shot ability, seamless code-switching capability, and speed control efficiency. Demo samples can be found at https://SWivid.github.io/F5-TTS. We release all code and checkpoints to promote community development.

CoT-ST: Enhancing LLM-based Speech Translation with Multimodal Chain-of-Thought

Speech Language Models (SLMs) have demonstrated impressive performance on speech translation tasks. However, existing research primarily focuses on direct instruction fine-tuning and often overlooks the inherent reasoning capabilities of SLMs. In this paper, we introduce a three-stage training framework designed to activate the chain-of-thought (CoT) capabilities of SLMs. We propose CoT-ST, a speech translation model that utilizes multimodal CoT to decompose speech translation into sequential steps of speech recognition and translation. We validated the effectiveness of our method on two datasets: the CoVoST-2 dataset and MuST-C dataset. The experimental results demonstrate that CoT-ST outperforms previous state-of-the-art methods, achieving higher BLEU scores (CoVoST-2 en-ja: 30.5->30.8, en-zh: 45.2->47.7, MuST-C en-zh: 19.6->21.2). This work is open sourced at https://github.com/X-LANCE/SLAM-LLM/tree/main/examples/st_covost2 .

Label-Synchronous Neural Transducer for E2E Simultaneous Speech Translation

While the neural transducer is popular for online speech recognition, simultaneous speech translation (SST) requires both streaming and re-ordering capabilities. This paper presents the LS-Transducer-SST, a label-synchronous neural transducer for SST, which naturally possesses these two properties. The LS-Transducer-SST dynamically decides when to emit translation tokens based on an Auto-regressive Integrate-and-Fire (AIF) mechanism. A latency-controllable AIF is also proposed, which can control the quality-latency trade-off either only during decoding, or it can be used in both decoding and training. The LS-Transducer-SST can naturally utilise monolingual text-only data via its prediction network which helps alleviate the key issue of data sparsity for E2E SST. During decoding, a chunk-based incremental joint decoding technique is designed to refine and expand the search space. Experiments on the Fisher-CallHome Spanish (Es-En) and MuST-C En-De data show that the LS-Transducer-SST gives a better quality-latency trade-off than existing popular methods. For example, the LS-Transducer-SST gives a 3.1/2.9 point BLEU increase (Es-En/En-De) relative to CAAT at a similar latency and a 1.4 s reduction in average lagging latency with similar BLEU scores relative to Wait-k.

Wav2Prompt: End-to-End Speech Prompt Generation and Tuning For LLM in Zero and Few-shot Learning

Wav2Prompt is proposed which allows straightforward integration between spoken input and a text-based large language model (LLM). Wav2Prompt uses a simple training process with only the same data used to train an automatic speech recognition (ASR) model. After training, Wav2Prompt learns continuous representations from speech and uses them as LLM prompts. To avoid task over-fitting issues found in prior work and preserve the emergent abilities of LLMs, Wav2Prompt takes LLM token embeddings as the training targets and utilises a continuous integrate-and-fire mechanism for explicit speech-text alignment. Therefore, a Wav2Prompt-LLM combination can be applied to zero-shot spoken language tasks such as speech translation (ST), speech understanding (SLU), speech question answering (SQA) and spoken-query-based QA (SQQA). It is shown that for these zero-shot tasks, Wav2Prompt performs similarly to an ASR-LLM cascade and better than recent prior work. If relatively small amounts of task-specific paired data are available in few-shot scenarios, the Wav2Prompt-LLM combination can be end-to-end (E2E) fine-tuned. The Wav2Prompt-LLM combination then yields greatly improved results relative to an ASR-LLM cascade for the above tasks. For instance, for English-French ST with the BLOOMZ-7B1 LLM, a Wav2Prompt-LLM combination gave a 8.5 BLEU point increase over an ASR-LLM cascade.

FastInject: Injecting Unpaired Text Data into CTC-based ASR training

Recently, connectionist temporal classification (CTC)-based end-to-end (E2E) automatic speech recognition (ASR) models have achieved impressive results, especially with the development of self-supervised learning. However, E2E ASR models trained on paired speech-text data often suffer from domain shifts from training to testing. To alleviate this issue, this paper proposes a flat-start joint training method, named FastInject, which efficiently injects multi-domain unpaired text data into CTC-based ASR training. To maintain training efficiency, text units are pre-upsampled, and their representations are fed into the CTC model along with speech features. To bridge the modality gap between speech and text, an attention-based modality matching mechanism (AM3) is proposed, which retains the E2E flat-start training. Experiments show that the proposed FastInject gave a 22\% relative WER reduction (WERR) for intra-domain Librispeech-100h data and 20\% relative WERR on out-of-domain test sets.

Label-Synchronous Neural Transducer for Adaptable Online E2E Speech Recognition

Although end-to-end (E2E) automatic speech recognition (ASR) has shown state-of-the-art recognition accuracy, it tends to be implicitly biased towards the training data distribution which can degrade generalisation. This paper proposes a label-synchronous neural transducer (LS-Transducer), which provides a natural approach to domain adaptation based on text-only data. The LS-Transducer extracts a label-level encoder representation before combining it with the prediction network output. Since blank tokens are no longer needed, the prediction network performs as a standard language model, which can be easily adapted using text-only data. An Auto-regressive Integrate-and-Fire (AIF) mechanism is proposed to generate the label-level encoder representation while retaining low latency operation that can be used for streaming. In addition, a streaming joint decoding method is designed to improve ASR accuracy while retaining synchronisation with AIF. Experiments show that compared to standard neural transducers, the proposed LS-Transducer gave a 12.9% relative WER reduction (WERR) for intra-domain LibriSpeech data, as well as 21.4% and 24.6% relative WERRs on cross-domain TED-LIUM 2 and AESRC2020 data with an adapted prediction network.

Decoupled Structure for Improved Adaptability of End-to-End Models

Although end-to-end (E2E) trainable automatic speech recognition (ASR) has shown great success by jointly learning acoustic and linguistic information, it still suffers from the effect of domain shifts, thus limiting potential applications. The E2E ASR model implicitly learns an internal language model (LM) which characterises the training distribution of the source domain, and the E2E trainable nature makes the internal LM difficult to adapt to the target domain with text-only data To solve this problem, this paper proposes decoupled structures for attention-based encoder-decoder (Decoupled-AED) and neural transducer (Decoupled-Transducer) models, which can achieve flexible domain adaptation in both offline and online scenarios while maintaining robust intra-domain performance. To this end, the acoustic and linguistic parts of the E2E model decoder (or prediction network) are decoupled, making the linguistic component (i.e. internal LM) replaceable. When encountering a domain shift, the internal LM can be directly replaced during inference by a target-domain LM, without re-training or using domain-specific paired speech-text data. Experiments for E2E ASR models trained on the LibriSpeech-100h corpus showed that the proposed decoupled structure gave 15.1% and 17.2% relative word error rate reductions on the TED-LIUM 2 and AESRC2020 corpora while still maintaining performance on intra-domain data.

Label-Synchronous Neural Transducer for End-to-End ASR

Neural transducers provide a natural approach to streaming ASR. However, they augment output sequences with blank tokens which leads to challenges for domain adaptation using text data. This paper proposes a label-synchronous neural transducer (LS-Transducer), which extracts a label-level encoder representation before combining it with the prediction network output. Hence blank tokens are no longer needed and the prediction network can be easily adapted using text data. An Auto-regressive Integrate-and-Fire (AIF) mechanism is proposed to generate the label-level encoder representation while retaining the streaming property. In addition, a streaming joint decoding method is designed to improve ASR accuracy. Experiments show that compared to standard neural transducers, the proposed LS-Transducer gave a 10% relative WER reduction (WERR) for intra-domain Librispeech-100h data, as well as 17% and 19% relative WERRs on cross-domain TED-LIUM 2 and AESRC2020 data with an adapted prediction network.

Adaptable End-to-End ASR Models using Replaceable Internal LMs and Residual Softmax

End-to-end (E2E) automatic speech recognition (ASR) implicitly learns the token sequence distribution of paired audio-transcript training data. However, it still suffers from domain shifts from training to testing, and domain adaptation is still challenging. To alleviate this problem, this paper designs a replaceable internal language model (RILM) method, which makes it feasible to directly replace the internal language model (LM) of E2E ASR models with a target-domain LM in the decoding stage when a domain shift is encountered. Furthermore, this paper proposes a residual softmax (R-softmax) that is designed for CTC-based E2E ASR models to adapt to the target domain without re-training during inference. For E2E ASR models trained on the LibriSpeech corpus, experiments showed that the proposed methods gave a 2.6% absolute WER reduction on the Switchboard data and a 1.0% WER reduction on the AESRC2020 corpus while maintaining intra-domain ASR results.

Improving Streaming End-to-End ASR on Transformer-based Causal Models with Encoder States Revision Strategies

There is often a trade-off between performance and latency in streaming automatic speech recognition (ASR). Traditional methods such as look-ahead and chunk-based methods, usually require information from future frames to advance recognition accuracy, which incurs inevitable latency even if the computation is fast enough. A causal model that computes without any future frames can avoid this latency, but its performance is significantly worse than traditional methods. In this paper, we propose corresponding revision strategies to improve the causal model. Firstly, we introduce a real-time encoder states revision strategy to modify previous states. Encoder forward computation starts once the data is received and revises the previous encoder states after several frames, which is no need to wait for any right context. Furthermore, a CTC spike position alignment decoding algorithm is designed to reduce time costs brought by the revision strategy. Experiments are all conducted on Librispeech datasets. Fine-tuning on the CTC-based wav2vec2.0 model, our best method can achieve 3.7/9.2 WERs on test-clean/other sets, which is also competitive with the chunk-based methods and the knowledge distillation methods.