MinMo: A Multimodal Large Language Model for Seamless Voice Interaction

Recent advancements in large language models (LLMs) and multimodal speech-text models have laid the groundwork for seamless voice interactions, enabling real-time, natural, and human-like conversations. Previous models for voice interactions are categorized as native and aligned. Native models integrate speech and text processing in one framework but struggle with issues like differing sequence lengths and insufficient pre-training. Aligned models maintain text LLM capabilities but are often limited by small datasets and a narrow focus on speech tasks. In this work, we introduce MinMo, a Multimodal Large Language Model with approximately 8B parameters for seamless voice interaction. We address the main limitations of prior aligned multimodal models. We train MinMo through multiple stages of speech-to-text alignment, text-to-speech alignment, speech-to-speech alignment, and duplex interaction alignment, on 1.4 million hours of diverse speech data and a broad range of speech tasks. After the multi-stage training, MinMo achieves state-of-the-art performance across various benchmarks for voice comprehension and generation while maintaining the capabilities of text LLMs, and also facilitates full-duplex conversation, that is, simultaneous two-way communication between the user and the system. Moreover, we propose a novel and simple voice decoder that outperforms prior models in voice generation. The enhanced instruction-following capabilities of MinMo supports controlling speech generation based on user instructions, with various nuances including emotions, dialects, and speaking rates, and mimicking specific voices. For MinMo, the speech-to-text latency is approximately 100ms, full-duplex latency is approximately 600ms in theory and 800ms in practice. The MinMo project web page is https://funaudiollm.github.io/minmo, and the code and models will be released soon.

Planarian Neural Networks: Evolutionary Patterns from Basic Bilateria Shaping Modern Artificial Neural Network Architectures

This study examined the viability of enhancing the prediction accuracy of artificial neural networks (ANNs) in image classification tasks by developing ANNs with evolution patterns similar to those of biological neural networks. ResNet is a widely used family of neural networks with both deep and wide variants; therefore, it was selected as the base model for our investigation. The aim of this study is to improve the image classification performance of ANNs via a novel approach inspired by the biological nervous system architecture of planarians, which comprises a brain and two nerve cords. We believe that the unique neural architecture of planarians offers valuable insights into the performance enhancement of ANNs. The proposed planarian neural architecture-based neural network was evaluated on the CIFAR-10 and CIFAR-100 datasets. Our results indicate that the proposed method exhibits higher prediction accuracy than the baseline neural network models in image classification tasks. These findings demonstrate the significant potential of biologically inspired neural network architectures in improving the performance of ANNs in a wide range of applications.

Enhancing Multimodal Emotion Recognition through Multi-Granularity Cross-Modal Alignment

Multimodal emotion recognition (MER), leveraging speech and text, has emerged as a pivotal domain within human-computer interaction, demanding sophisticated methods for effective multimodal integration. The challenge of aligning features across these modalities is significant, with most existing approaches adopting a singular alignment strategy. Such a narrow focus not only limits model performance but also fails to address the complexity and ambiguity inherent in emotional expressions. In response, this paper introduces a Multi-Granularity Cross-Modal Alignment (MGCMA) framework, distinguished by its comprehensive approach encompassing distribution-based, instance-based, and token-based alignment modules. This framework enables a multi-level perception of emotional information across modalities. Our experiments on IEMOCAP demonstrate that our proposed method outperforms current state-of-the-art techniques.

Ensuring Consistency for In-Image Translation

The in-image machine translation task involves translating text embedded within images, with the translated results presented in image format. While this task has numerous applications in various scenarios such as film poster translation and everyday scene image translation, existing methods frequently neglect the aspect of consistency throughout this process. We propose the need to uphold two types of consistency in this task: translation consistency and image generation consistency. The former entails incorporating image information during translation, while the latter involves maintaining consistency between the style of the text-image and the original image, ensuring background integrity. To address these consistency requirements, we introduce a novel two-stage framework named HCIIT (High-Consistency In-Image Translation) which involves text-image translation using a multimodal multilingual large language model in the first stage and image backfilling with a diffusion model in the second stage. Chain of thought learning is utilized in the first stage to enhance the model's ability to leverage image information during translation. Subsequently, a diffusion model trained for style-consistent text-image generation ensures uniformity in text style within images and preserves background details. A dataset comprising 400,000 style-consistent pseudo text-image pairs is curated for model training. Results obtained on both curated test sets and authentic image test sets validate the effectiveness of our framework in ensuring consistency and producing high-quality translated images.

Interleaved Speech-Text Language Models are Simple Streaming Text to Speech Synthesizers

This paper introduces Interleaved Speech-Text Language Model (IST-LM) for streaming zero-shot Text-to-Speech (TTS). Unlike many previous approaches, IST-LM is directly trained on interleaved sequences of text and speech tokens with a fixed ratio, eliminating the need for additional efforts in duration prediction and grapheme-to-phoneme alignment. The ratio of text chunk size to speech chunk size is crucial for the performance of IST-LM. To explore this, we conducted a comprehensive series of statistical analyses on the training data and performed correlation analysis with the final performance, uncovering several key factors: 1) the distance between speech tokens and their corresponding text tokens, 2) the number of future text tokens accessible to each speech token, and 3) the frequency of speech tokens precedes their corresponding text tokens. Experimental results demonstrate how to achieve an optimal streaming TTS system without complicated engineering optimization, which has a limited gap with the non-streaming system. IST-LM is conceptually simple and empirically powerful, paving the way for streaming TTS with minimal overhead while largely maintaining performance, showcasing broad prospects coupled with real-time text stream from LLMs.

Correcting Large Language Model Behavior via Influence Function

Recent advancements in AI alignment techniques have significantly improved the alignment of large language models (LLMs) with static human preferences. However, the dynamic nature of human preferences can render some prior training data outdated or even erroneous, ultimately causing LLMs to deviate from contemporary human preferences and societal norms. Existing methodologies, whether they involve the curation of new data for continual alignment or the manual correction of outdated data for re-alignment, demand costly human resources. To address this challenge, we propose a novel approach, Large Language Model Behavior Correction with Influence Function Recall and Post-Training (LANCET), which requires no human involvement. LANCET consists of two phases: (1) using influence functions to identify the training data that significantly impact undesirable model outputs, and (2) applying an Influence function-driven Bregman Optimization (IBO) technique to adjust the model's behavior based on these influence distributions. Our experiments demonstrate that LANCET effectively and efficiently correct inappropriate behaviors of LLMs. Furthermore, LANCET can outperform methods that rely on collecting human preferences, and it enhances the interpretability of learning human preferences within LLMs.

Centaur: Bridging the Impossible Trinity of Privacy, Efficiency, and Performance in Privacy-Preserving Transformer Inference

As pre-trained models, like Transformers, are increasingly deployed on cloud platforms for inference services, the privacy concerns surrounding model parameters and inference data are becoming more acute. Current Privacy-Preserving Transformer Inference (PPTI) frameworks struggle with the "impossible trinity" of privacy, efficiency, and performance. For instance, Secure Multi-Party Computation (SMPC)-based solutions offer strong privacy guarantees but come with significant inference overhead and performance trade-offs. On the other hand, PPTI frameworks that use random permutations achieve inference efficiency close to that of plaintext and maintain accurate results but require exposing some model parameters and intermediate results, thereby risking substantial privacy breaches. Addressing this "impossible trinity" with a single technique proves challenging. To overcome this challenge, we propose Centaur, a novel hybrid PPTI framework. Unlike existing methods, Centaur protects model parameters with random permutations and inference data with SMPC, leveraging the structure of Transformer models. By designing a series of efficient privacy-preserving algorithms, Centaur leverages the strengths of both techniques to achieve a better balance between privacy, efficiency, and performance in PPTI. We comprehensively evaluate the effectiveness of Centaur on various types of Transformer models and datasets. Experimental results demonstrate that the privacy protection capabilities offered by Centaur can withstand various existing model inversion attack methods. In terms of performance and efficiency, Centaur not only maintains the same performance as plaintext inference but also improves inference speed by $5.0-30.4$ times.

CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models

In our previous work, we introduced CosyVoice, a multilingual speech synthesis model based on supervised discrete speech tokens. By employing progressive semantic decoding with two popular generative models, language models (LMs) and Flow Matching, CosyVoice demonstrated high prosody naturalness, content consistency, and speaker similarity in speech in-context learning. Recently, significant progress has been made in multi-modal large language models (LLMs), where the response latency and real-time factor of speech synthesis play a crucial role in the interactive experience. Therefore, in this report, we present an improved streaming speech synthesis model, CosyVoice 2, which incorporates comprehensive and systematic optimizations. Specifically, we introduce finite-scalar quantization to improve the codebook utilization of speech tokens. For the text-speech LM, we streamline the model architecture to allow direct use of a pre-trained LLM as the backbone. In addition, we develop a chunk-aware causal flow matching model to support various synthesis scenarios, enabling both streaming and non-streaming synthesis within a single model. By training on a large-scale multilingual dataset, CosyVoice 2 achieves human-parity naturalness, minimal response latency, and virtually lossless synthesis quality in the streaming mode. We invite readers to listen to the demos at https://funaudiollm.github.io/cosyvoice2.

Addressing bias in Recommender Systems: A Case Study on Data Debiasing Techniques in Mobile Games

The mobile gaming industry, particularly the free-to-play sector, has been around for more than a decade, yet it still experiences rapid growth. The concept of games-as-service requires game developers to pay much more attention to recommendations of content in their games. With recommender systems (RS), the inevitable problem of bias in the data comes hand in hand. A lot of research has been done on the case of bias in RS for online retail or services, but much less is available for the specific case of the game industry. Also, in previous works, various debiasing techniques were tested on explicit feedback datasets, while it is much more common in mobile gaming data to only have implicit feedback. This case study aims to identify and categorize potential bias within datasets specific to model-based recommendations in mobile games, review debiasing techniques in the existing literature, and assess their effectiveness on real-world data gathered through implicit feedback. The effectiveness of these methods is then evaluated based on their debiasing quality, data requirements, and computational demands.

Transcending Language Boundaries: Harnessing LLMs for Low-Resource Language Translation

Large Language Models (LLMs) have demonstrated remarkable success across a wide range of tasks and domains. However, their performance in low-resource language translation, particularly when translating into these languages, remains underexplored. This gap poses significant challenges, as linguistic barriers hinder the cultural preservation and development of minority communities. To address this issue, this paper introduces a novel retrieval-based method that enhances translation quality for low-resource languages by focusing on key terms, which involves translating keywords and retrieving corresponding examples from existing data. To evaluate the effectiveness of this method, we conducted experiments translating from English into three low-resource languages: Cherokee, a critically endangered indigenous language of North America; Tibetan, a historically and culturally significant language in Asia; and Manchu, a language with few remaining speakers. Our comparison with the zero-shot performance of GPT-4o and LLaMA 3.1 405B, highlights the significant challenges these models face when translating into low-resource languages. In contrast, our retrieval-based method shows promise in improving both word-level accuracy and overall semantic understanding by leveraging existing resources more effectively.