Java SDK

import java.io.File;
import java.io.FileInputStream;
import java.io.IOException;
import com.alibaba.nls.client.protocol.InputFormatEnum;
import com.alibaba.nls.client.protocol.NlsClient;
import com.alibaba.nls.client.protocol.SampleRateEnum;
import com.alibaba.nls.client.protocol.asr.SpeechRecognizer;
import com.alibaba.nls.client.protocol.asr.SpeechRecognizerListener;
import com.alibaba.nls.client.protocol.asr.SpeechRecognizerResponse;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
/**
 * 此樣本示範了：
 *      ASR一句話識別API調用。
 *      動態擷取Token。擷取Token具體操作，請參見：https://help.aliyun.com/document_detail/450514.html
 *      通過本地檔案類比即時資料流發送。
 *      識別耗時計算。
 */
public class SpeechRecognizerDemo {
    private static final Logger logger = LoggerFactory.getLogger(SpeechRecognizerDemo.class);
    private String appKey;
    NlsClient client;
    public SpeechRecognizerDemo(String appKey, String id, String secret, String url) {
        this.appKey = appKey;
        //應用全域建立一個NlsClient執行個體，預設服務地址為阿里雲線上服務地址。
        //擷取Token，實際使用時注意在accessToken.getExpireTime()到期前再次擷取。
        AccessToken accessToken = new AccessToken(id, secret);
        try {
            accessToken.apply();
            System.out.println("get token: " + accessToken.getToken() + ", expire time: " + accessToken.getExpireTime());
            if(url.isEmpty()) {
                client = new NlsClient(accessToken.getToken());
            }else {
                client = new NlsClient(url, accessToken.getToken());
            }
        } catch (IOException e) {
            e.printStackTrace();
        }
    }
    private static SpeechRecognizerListener getRecognizerListener(int myOrder, String userParam) {
        SpeechRecognizerListener listener = new SpeechRecognizerListener() {
            //識別出中間結果。僅當setEnableIntermediateResult為true時，才會返回該訊息。
            @Override
            public void onRecognitionResultChanged(SpeechRecognizerResponse response) {
                //getName是擷取事件名稱，getStatus是擷取狀態代碼，getRecognizedText是語音辨識文本。
                System.out.println("name: " + response.getName() + ", status: " + response.getStatus() + ", result: " + response.getRecognizedText());
            }
            //識別完畢
            @Override
            public void onRecognitionCompleted(SpeechRecognizerResponse response) {
                //getName是擷取事件名稱，getStatus是擷取狀態代碼，getRecognizedText是語音辨識文本。
                System.out.println("name: " + response.getName() + ", status: " + response.getStatus() + ", result: " + response.getRecognizedText());
            }
            @Override
            public void onStarted(SpeechRecognizerResponse response) {
                System.out.println("myOrder: " + myOrder + "; myParam: " + userParam + "; task_id: " + response.getTaskId());
            }
            @Override
            public void onFail(SpeechRecognizerResponse response) {
                //task_id是調用方和服務端通訊的唯一標識，當遇到問題時，需要提供此task_id。
                System.out.println("task_id: " + response.getTaskId() + ", status: " + response.getStatus() + ", status_text: " + response.getStatusText());
            }
        };
        return listener;
    }
    //根據位元據大小計算對應的同等語音長度
    //sampleRate僅支援8000或16000。
    public static int getSleepDelta(int dataSize, int sampleRate) {
        // 僅支援16位採樣。
        int sampleBytes = 16;
        // 僅支援單通道。
        int soundChannel = 1;
        return (dataSize * 10 * 8000) / (160 * sampleRate);
    }
    public void process(String filepath, int sampleRate) {
        SpeechRecognizer recognizer = null;
        try {
            //傳遞使用者自訂參數
            String myParam = "user-param";
            int myOrder = 1234;
            SpeechRecognizerListener listener = getRecognizerListener(myOrder, myParam);
            recognizer = new SpeechRecognizer(client, listener);
            recognizer.setAppKey(appKey);
            //設定音頻編碼格式。如果是OPUS檔案，請設定為InputFormatEnum.OPUS。
            recognizer.setFormat(InputFormatEnum.PCM);
            //設定音頻採樣率
            if(sampleRate == 16000) {
                recognizer.setSampleRate(SampleRateEnum.SAMPLE_RATE_16K);
            } else if(sampleRate == 8000) {
                recognizer.setSampleRate(SampleRateEnum.SAMPLE_RATE_8K);
            }
            //設定是否返回中間識別結果
            recognizer.setEnableIntermediateResult(true);
            //設定是否開啟語音檢測（即vad）
   recognizer.addCustomedParam("enable_voice_detection",true);
            //此方法將以上參數設定序列化為JSON發送給服務端，並等待服務端確認。
            long now = System.currentTimeMillis();
            recognizer.start();
            logger.info("ASR start latency : " + (System.currentTimeMillis() - now) + " ms");
            File file = new File(filepath);
            FileInputStream fis = new FileInputStream(file);
            byte[] b = new byte[3200];
            int len;
            while ((len = fis.read(b)) > 0) {
                logger.info("send data pack length: " + len);
                recognizer.send(b, len);
                //本案例用讀取本地檔案的形式類比即時擷取語音流，因為讀取速度較快，這裡需要設定sleep時間長度。
                // 如果即時擷取語音則無需設定sleep時間長度，如果是8k採樣率語音第二個參數設定為8000。
                int deltaSleep = getSleepDelta(len, sampleRate);
                Thread.sleep(deltaSleep);
            }
            //通知服務端語音資料發送完畢，等待服務端處理完成。
            now = System.currentTimeMillis();
            //計算實際延遲，調用stop返回之後一般即是識別結果返回時間。
            logger.info("ASR wait for complete");
            recognizer.stop();
            logger.info("ASR stop latency : " + (System.currentTimeMillis() - now) + " ms");
            fis.close();
        } catch (Exception e) {
            System.err.println(e.getMessage());
        } finally {
            //關閉串連
            if (null != recognizer) {
                recognizer.close();
            }
        }
    }
    public void shutdown() {
        client.shutdown();
    }
    public static void main(String[] args) throws Exception {
        String appKey = System.getenv().get("NLS_APP_KEY");
        String id = System.getenv().get("ALIYUN_AK_ID");
        String secret = System.getenv().get("ALIYUN_AK_SECRET");
        String url = System.getenv().getOrDefault("NLS_GATEWAY_URL", "wss://nls-gateway-cn-shanghai.aliyuncs.com/ws/v1");
        SpeechRecognizerDemo demo = new SpeechRecognizerDemo(appKey, id, secret, url);
        //本案例使用本地檔案類比發送即時資料流資料。
        demo.process("./nls-sample-16k.wav", 16000);
        //demo.process("./nls-sample.opus", 16000);
        demo.shutdown();
    }
}