3.AI large model voice interaction

1. Concept Introduction

1.1 What is "AI Large Model Voice Interaction"?

In the largemodel project, AI Large Model Voice Interaction combines the offline ASR and offline TTS described above with the large language model (LLM) core to form a complete conversational system that listens, speaks, and thinks.

This is no longer an isolated function, but rather the prototype of a true voice assistant. Users can engage in natural language conversations with the robot through voice, and the robot can understand questions, think about answers, and respond with voice. This entire process is completed locally, without the need for a network.

The core of this function is the model_service` ROS2 node. It acts as the brain and neural center, subscribing to ASR recognition results, invoking the LLM for thinking, and then publishing the LLM's text responses to the TTS node for speech synthesis.

1.2 Implementation Principle

This feature is implemented using a classic data flow pipeline:

1. Audio -> Text (ASR): The asr node continuously listens to ambient sound. Once it detects a user speaking a sentence, it converts it into text and publishes it to the /asr_text topic.
2. Text -> Thought -> Text (LLM): The model_service node subscribes to the /asr_text topic. Upon receiving the text from the ASR, it passes it as a prompt to a locally deployed large language model (such as Qwen running through Ollama). The LLM generates a text response based on the context.
3. Text -> Audio (TTS): After receiving the LLM's response, the model_service node publishes it to the /tts_text topic.
4. Audio Playback: The tts_only node subscribes to the /tts_text topic. Upon receiving text, it immediately invokes the offline TTS model to synthesize it into audio and plays it through the speaker.

This process forms a complete closed loop: speech input -> text processing -> text output -> speech output.

2. Code Analysis

Key Code

1. Voice Input Node (largemodel/largemodel/asr.py)

​x
# From largemodel/largemodel/asr.py
class ASRNode(Node):
    def __init__(self):
        # ...
        self.asr_pub = self.create_publisher(String, "asr", 5)
        # ...
​
    def kws_handler(self)->None:
        if self.listen_for_speech(self.mic_index):
            asr_text = self.ASR_conversion(self.user_speechdir)
            if asr_text != 'error':
                self.asr_pub_result(asr_text)
​
    def asr_pub_result(self,asr_result:str)->None:
        msg=String(data=asr_result)
        self.asr_pub.publish(msg)

2. AI service and voice output node (largemodel/largemodel/model_service.py)

xxxxxxxxxx
# From largemodel/largemodel/model_service.py
class LargeModelService(Node):
    def __init__(self):
        # ...
        self.asrsub = self.create_subscription(String,'asr', self.asr_callback,1)
        # ...
​
    def asr_callback(self,msg):
        """Callback function for handling ASR messages. / 处理ASR消息的回调函数。"""
        # ...
        result = self.model_client.infer_with_text(msg.data, message=messages_to_use)
        self.process_model_result(result)
​
    def process_model_result(self, result, from_seewhat=False):
        """Process the result returned by the model. / 处理模型返回的结果。"""
        # ...
        user_friendly_response = response_json.get("response", "我正在处理...")
        # ...
        self._safe_play_audio(user_friendly_response)
        # ...
        self.execute_tools(tools_list)
​
    def _safe_play_audio(self, text_to_speak: str):
        """
        Synthesizes and plays all non-empty messages only in non-text chat mode.
        """
        if not self.text_chat_mode and text_to_speak:
            try:
                self.model_client.voice_synthesis(text_to_speak, self.tts_out_path)
                self.play_audio_async(self.tts_out_path)
            except Exception as e:
                self.get_logger().error(f"Safe audio playback failed: {e}")

Code Analysis

The voice interaction functionality of the large AI model is implemented by two independent ROS nodes, asr.py and model_service.py, which communicate via the ROS topic /asr, forming a complete processing loop.

1. Voice Input and Publishing (asr.py):

• The ASRNode node processes voice input. In the kws_handler function, it performs audio recording and text conversion.
• After successful conversion, the asr_pub_result function is called. This function places the resulting text string into a std_msgs.msg.String message and then publishes it to the /asr topic via the self.asr_pub publisher.

2. Subscription and Response (model_service.py):

• During initialization, the LargeModelService node subscribes to the /asr topic using the create_subscription method and specifies asr_callback as its callback function.
• When ASRNode publishes a message on the /asr topic, the ROS system automatically calls the asr_callback function of LargeModelService, passing the message as the msg parameter.

3. Interaction Loop:

• After receiving the message, the asr_callback function extracts the text data (msg.data) and passes it to the large model for inference (self.model_client.infer_with_text).
• After inference is complete, the process_model_result function is called. This function extracts the reply text from the model result.
• Next, the _safe_play_audio function is called, which uses the TTS function (self.model_client.voice_synthesis) to synthesize the reply text into audio and play it back.
• At this point, a complete interaction loop from "receiving user voice" to "responding to the user with voice" is completed. The two nodes are decoupled using the ROS publish-subscribe model. asr.py handles input, while model_service.py handles processing and output.

3. Practical Operations

3.1 Configuring Offline Voice Interaction

To implement a fully offline voice interaction system, you need to ensure that all three components, ASR, TTS, and LLM, are configured for offline mode.

1. Open the main configuration file yahboom.yaml:

   xxxxxxxxxx
   gedit ~/yahboom_ws/src/largemodel/config/yahboom.yaml
   

2. Modify/confirm the following key configurations:

   xxxxxxxxxx
   asr:
     ros__parameters:
       use_oline_asr: False                # Key: Set to False to enable offline ASR
       regional_setting : "international" 
   ​
   model_service:
     ros__parameters:
       useolinetts: False                   # Key: Set to False to enable offline TTS
       llm_platform: 'ollama'              # Key: Set to 'ollama' to enable offline LLM
   regional_setting : "international" 
   

3. Open the model interface configuration file large_model_interface.yaml:

   xxxxxxxxxx
   gedit ~/yahboom_ws/src/largemodel/config/large_model_interface.yaml
   

4. Confirm that all offline model paths are correct:

   xxxxxxxxxx
   # large_model_interface.yaml
   ​
   ## Offline large model
   ollama_model: "qwen2.5:7b"  # Make sure the model has been downloaded via ollama pull
   ​
   ## Offline speech recognition
   local_asr_model: "/path/to/your/SenseVoiceSmall" # Make sure the ASR model path is correct
   ​
   ## Offline speech synthesis
   zh_tts_model: "/path/to/your/zh_CN-huayan-medium.onnx" # Make sure the TTS model path is correct
   # ...
   

If you have modified any configuration files, please run the following command to compile the ROS workspace for the configuration to take effect.

xxxxxxxxxx
cd ~/yahboom_ws
colcon build

3.2 Starting and Testing the Function

1. Start largemodel main program: Run the following command to enable voice interaction:

   xxxxxxxxxx
   ros2 launch largemodel largemodel_control.launch.py
   

2. Test:

   • Wake up: Say "Hi, yahboom" into the microphone.
   • Dialogue: After the speaker responds, you can speak your questions.
   • Observe the log: In the terminal running the launch file, you should see the following:
   1. The ASR node recognizes your question and prints it.
   2. The model_service node receives the text, calls the LLM, and prints the LLM's response.
   • Listen to the answer: After a while, you should hear the robot's synthesized voice answer your question through the speaker.